feat: Add yolov5n, update docs and ruff code format

* ref: Remove type conversion and update face class

* fix: change the type to float32

* chore: Update all examples, testing with latest version

* docs: Update docs reflecting the recent changes

CONTRIBUTING.md

@@ -0,0 +1,60 @@
+# Contributing to UniFace
+
+Thank you for considering contributing to UniFace! We welcome contributions of all kinds.
+
+## How to Contribute
+
+### Reporting Issues
+
+- Use GitHub Issues to report bugs or suggest features
+- Include clear descriptions and reproducible examples
+- Check existing issues before creating new ones
+
+### Pull Requests
+
+1. Fork the repository
+2. Create a new branch for your feature
+3. Write clear, documented code with type hints
+4. Add tests for new functionality
+5. Ensure all tests pass
+6. Submit a pull request with a clear description
+
+### Code Style
+
+- Follow PEP8 guidelines
+- Use type hints (Python 3.10+)
+- Write docstrings for public APIs
+- Keep code simple and readable
+
+## Development Setup
+
+```bash
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+pip install -e ".[dev]"
+```
+
+## Running Tests
+
+```bash
+pytest tests/
+```
+
+## Examples
+
+Example notebooks demonstrating library usage:
+
+| Example | Notebook |
+|---------|----------|
+| Face Detection | [face_detection.ipynb](examples/face_detection.ipynb) |
+| Face Alignment | [face_alignment.ipynb](examples/face_alignment.ipynb) |
+| Face Recognition | [face_analyzer.ipynb](examples/face_analyzer.ipynb) |
+| Face Verification | [face_verification.ipynb](examples/face_verification.ipynb) |
+| Face Search | [face_search.ipynb](examples/face_search.ipynb) |
+
+## Questions?
+
+Open an issue or start a discussion on GitHub.
+
+
+

MODELS.md

@@ -10,14 +10,14 @@ Complete guide to all available models, their performance characteristics, and s
 
 RetinaFace models are trained on the WIDER FACE dataset and provide excellent accuracy-speed tradeoffs.
 
-| Model Name          | Params | Size   | Easy   | Medium | Hard   | Use Case                    |
-|---------------------|--------|--------|--------|--------|--------|----------------------------|
-| `MNET_025`          | 0.4M   | 1.7MB  | 88.48% | 87.02% | 80.61% | Mobile/Edge devices         |
-| `MNET_050`          | 1.0M   | 2.6MB  | 89.42% | 87.97% | 82.40% | Mobile/Edge devices         |
-| `MNET_V1`           | 3.5M   | 3.8MB  | 90.59% | 89.14% | 84.13% | Balanced mobile             |
-| `MNET_V2` ⭐        | 3.2M   | 3.5MB  | 91.70% | 91.03% | 86.60% | **Recommended default**     |
-| `RESNET18`          | 11.7M  | 27MB   | 92.50% | 91.02% | 86.63% | Server/High accuracy        |
-| `RESNET34`          | 24.8M  | 56MB   | 94.16% | 93.12% | 88.90% | Maximum accuracy            |
+| Model Name     | Params | Size  | Easy   | Medium | Hard   | Use Case                      |
+| -------------- | ------ | ----- | ------ | ------ | ------ | ----------------------------- |
+| `MNET_025`   | 0.4M   | 1.7MB | 88.48% | 87.02% | 80.61% | Mobile/Edge devices           |
+| `MNET_050`   | 1.0M   | 2.6MB | 89.42% | 87.97% | 82.40% | Mobile/Edge devices           |
+| `MNET_V1`    | 3.5M   | 3.8MB | 90.59% | 89.14% | 84.13% | Balanced mobile               |
+| `MNET_V2` ⭐ | 3.2M   | 3.5MB | 91.70% | 91.03% | 86.60% | **Recommended default** |
+| `RESNET18`   | 11.7M  | 27MB  | 92.50% | 91.02% | 86.63% | Server/High accuracy          |
+| `RESNET34`   | 24.8M  | 56MB  | 94.16% | 93.12% | 88.90% | Maximum accuracy              |
 
 **Accuracy**: WIDER FACE validation set (Easy/Medium/Hard subsets) - from [RetinaFace paper](https://arxiv.org/abs/1905.00641)
 **Speed**: Benchmark on your own hardware using `scripts/run_detection.py --iterations 100`
@@ -46,10 +46,10 @@ detector = RetinaFace(
 
 SCRFD (Sample and Computation Redistribution for Efficient Face Detection) models offer state-of-the-art speed-accuracy tradeoffs.
 
-| Model Name      | Params | Size  | Easy   | Medium | Hard   | Use Case                    |
-|-----------------|--------|-------|--------|--------|--------|----------------------------|
-| `SCRFD_500M`    | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% | Real-time applications      |
-| `SCRFD_10G` ⭐  | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% | **High accuracy + speed**   |
+| Model Name       | Params | Size  | Easy   | Medium | Hard   | Use Case                        |
+| ---------------- | ------ | ----- | ------ | ------ | ------ | ------------------------------- |
+| `SCRFD_500M`   | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% | Real-time applications          |
+| `SCRFD_10G` ⭐ | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% | **High accuracy + speed** |
 
 **Accuracy**: WIDER FACE validation set - from [SCRFD paper](https://arxiv.org/abs/2105.04714)
 **Speed**: Benchmark on your own hardware using `scripts/run_detection.py --iterations 100`
@@ -76,16 +76,66 @@ detector = SCRFD(
 
 ---
 
+### YOLOv5-Face Family
+
+YOLOv5-Face models provide excellent detection accuracy with 5-point facial landmarks, optimized for real-time applications.
+
+| Model Name     | Size | Easy   | Medium | Hard   | Use Case                       |
+| -------------- | ---- | ------ | ------ | ------ | ------------------------------ |
+| `YOLOV5N`    | 11MB | 93.61% | 91.52% | 80.53% | Lightweight/Mobile             |
+| `YOLOV5S` ⭐ | 28MB | 94.33% | 92.61% | 83.15% | **Real-time + accuracy** |
+| `YOLOV5M`    | 82MB | 95.30% | 93.76% | 85.28% | High accuracy                  |
+
+**Accuracy**: WIDER FACE validation set - from [YOLOv5-Face paper](https://arxiv.org/abs/2105.12931)
+**Speed**: Benchmark on your own hardware using `scripts/run_detection.py --iterations 100`
+**Note**: Fixed input size of 640×640. Models exported to ONNX from [deepcam-cn/yolov5-face](https://github.com/deepcam-cn/yolov5-face)
+
+#### Usage
+
+```python
+from uniface import YOLOv5Face
+from uniface.constants import YOLOv5FaceWeights
+
+# Lightweight/Mobile
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5N,
+    conf_thresh=0.6,
+    nms_thresh=0.5
+)
+
+# Real-time detection (recommended)
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    conf_thresh=0.6,
+    nms_thresh=0.5
+)
+
+# High accuracy
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5M,
+    conf_thresh=0.6
+)
+
+# Detect faces with landmarks
+faces = detector.detect(image)
+for face in faces:
+    bbox = face['bbox']  # [x1, y1, x2, y2]
+    confidence = face['confidence']
+    landmarks = face['landmarks']  # 5-point landmarks (5, 2)
+```
+
+---
+
 ## Face Recognition Models
 
 ### ArcFace
 
 State-of-the-art face recognition using additive angular margin loss.
 
-| Model Name  | Backbone    | Params | Size  | Use Case                    |
-|-------------|-------------|--------|-------|----------------------------|
-| `MNET` ⭐   | MobileNet   | 2.0M   | 8MB   | **Balanced (recommended)** |
-| `RESNET`    | ResNet50    | 43.6M  | 166MB | Maximum accuracy           |
+| Model Name  | Backbone  | Params | Size  | Use Case                         |
+| ----------- | --------- | ------ | ----- | -------------------------------- |
+| `MNET` ⭐ | MobileNet | 2.0M   | 8MB   | **Balanced (recommended)** |
+| `RESNET`  | ResNet50  | 43.6M  | 166MB | Maximum accuracy                 |
 
 **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
 **Accuracy**: Benchmark on your own dataset or use standard face verification benchmarks
@@ -113,13 +163,15 @@ embedding = recognizer.get_normalized_embedding(image, landmarks)
 
 Lightweight face recognition optimized for mobile devices.
 
-| Model Name      | Backbone        | Params | Size | Use Case           |
-|-----------------|-----------------|--------|------|--------------------|
-| `MNET_025`      | MobileNetV1 0.25| 0.2M   | 1MB  | Ultra-lightweight  |
-| `MNET_V2` ⭐    | MobileNetV2     | 1.0M   | 4MB  | **Mobile/Edge**    |
-| `MNET_V3_SMALL` | MobileNetV3-S   | 0.8M   | 3MB  | Mobile optimized   |
-| `MNET_V3_LARGE` | MobileNetV3-L   | 2.5M   | 10MB | Balanced mobile    |
+| Model Name        | Backbone         | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 | Use Case              |
+| ----------------- | ---------------- | ------ | ---- | ------ | ------ | ------ | -------- | --------------------- |
+| `MNET_025`      | MobileNetV1 0.25 | 0.36M  | 1MB  | 98.76% | 92.02% | 82.37% | 90.02%   | Ultra-lightweight     |
+| `MNET_V2` ⭐    | MobileNetV2      | 2.29M  | 4MB  | 99.55% | 94.87% | 86.89% | 95.16%   | **Mobile/Edge** |
+| `MNET_V3_SMALL` | MobileNetV3-S    | 1.25M  | 3MB  | 99.30% | 93.77% | 85.29% | 92.79%   | Mobile optimized      |
+| `MNET_V3_LARGE` | MobileNetV3-L    | 3.52M  | 10MB | 99.53% | 94.56% | 86.79% | 95.13%   | Balanced mobile       |
 
+**Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+**Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
 **Note**: These models are lightweight alternatives to ArcFace for resource-constrained environments
 
 #### Usage
@@ -138,12 +190,14 @@ recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)
 
 Face recognition using angular softmax loss.
 
-| Model Name  | Backbone | Params | Size | Use Case              |
-|-------------|----------|--------|------|----------------------|
-| `SPHERE20`  | Sphere20 | 13.0M  | 50MB | Research/Comparison  |
-| `SPHERE36`  | Sphere36 | 24.2M  | 92MB | Research/Comparison  |
+| Model Name   | Backbone | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 | Use Case            |
+| ------------ | -------- | ------ | ---- | ------ | ------ | ------ | -------- | ------------------- |
+| `SPHERE20` | Sphere20 | 24.5M  | 50MB | 99.67% | 95.61% | 88.75% | 96.58%   | Research/Comparison |
+| `SPHERE36` | Sphere36 | 34.6M  | 92MB | 99.72% | 95.64% | 89.92% | 96.83%   | Research/Comparison |
 
-**Note**: SphereFace uses angular softmax loss, an earlier approach before ArcFace
+**Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+**Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
+**Note**: SphereFace uses angular softmax loss, an earlier approach before ArcFace. These models provide good accuracy with moderate resource requirements.
 
 #### Usage
 
@@ -162,9 +216,9 @@ recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)
 
 High-precision facial landmark localization.
 
-| Model Name | Points | Params | Size | Use Case                    |
-|------------|--------|--------|------|-----------------------------|
-| `2D106`    | 106    | 3.7M   | 14MB | Face alignment, analysis    |
+| Model Name | Points | Params | Size | Use Case                 |
+| ---------- | ------ | ------ | ---- | ------------------------ |
+| `2D106`  | 106    | 3.7M   | 14MB | Face alignment, analysis |
 
 **Note**: Provides 106 facial keypoints for detailed face analysis and alignment
 
@@ -179,6 +233,7 @@ landmarks = landmarker.get_landmarks(image, bbox)
 ```
 
 **Landmark Groups:**
+
 - Face contour: 0-32 (33 points)
 - Eyebrows: 33-50 (18 points)
 - Nose: 51-62 (12 points)
@@ -191,9 +246,9 @@ landmarks = landmarker.get_landmarks(image, bbox)
 
 ### Age & Gender Detection
 
-| Model Name | Attributes  | Params | Size | Use Case           |
-|------------|-------------|--------|------|-------------------|
-| `DEFAULT`  | Age, Gender | 2.1M   | 8MB  | General purpose   |
+| Model Name  | Attributes  | Params | Size | Use Case        |
+| ----------- | ----------- | ------ | ---- | --------------- |
+| `DEFAULT` | Age, Gender | 2.1M   | 8MB  | General purpose |
 
 **Dataset**: Trained on CelebA
 **Note**: Accuracy varies by demographic and image quality. Test on your specific use case.
@@ -205,17 +260,18 @@ from uniface import AgeGender
 
 predictor = AgeGender()
 gender, age = predictor.predict(image, bbox)
-# Returns: ("Male"/"Female", age_in_years)
+# Returns: (gender, age_in_years)
+# gender: 0 for Female, 1 for Male
 ```
 
 ---
 
 ### Emotion Detection
 
-| Model Name   | Classes | Params | Size | Use Case              |
-|--------------|---------|--------|------|-----------------------|
-| `AFFECNET7`  | 7       | 0.5M   | 2MB  | 7-class emotion       |
-| `AFFECNET8`  | 8       | 0.5M   | 2MB  | 8-class emotion       |
+| Model Name    | Classes | Params | Size | Use Case        |
+| ------------- | ------- | ------ | ---- | --------------- |
+| `AFFECNET7` | 7       | 0.5M   | 2MB  | 7-class emotion |
+| `AFFECNET8` | 8       | 0.5M   | 2MB  | 8-class emotion |
 
 **Classes (7)**: Neutral, Happy, Sad, Surprise, Fear, Disgust, Anger
 **Classes (8)**: Above + Contempt
@@ -235,118 +291,6 @@ emotion, confidence = predictor.predict(image, landmarks)
 
 ---
 
-## Model Selection Guide
-
-### By Use Case
-
-#### Mobile/Edge Devices
-- **Detection**: `RetinaFace(MNET_025)` or `SCRFD(SCRFD_500M)`
-- **Recognition**: `MobileFace(MNET_V2)`
-- **Priority**: Speed, small model size
-
-#### Real-Time Applications (Webcam, Video)
-- **Detection**: `RetinaFace(MNET_V2)` or `SCRFD(SCRFD_500M)`
-- **Recognition**: `ArcFace(MNET)`
-- **Priority**: Speed-accuracy balance
-
-#### High-Accuracy Applications (Security, Verification)
-- **Detection**: `SCRFD(SCRFD_10G)` or `RetinaFace(RESNET34)`
-- **Recognition**: `ArcFace(RESNET)`
-- **Priority**: Maximum accuracy
-
-#### Server/Cloud Deployment
-- **Detection**: `SCRFD(SCRFD_10G)`
-- **Recognition**: `ArcFace(RESNET)`
-- **Priority**: Accuracy, batch processing
-
----
-
-### By Hardware
-
-#### Apple Silicon (M1/M2/M3/M4)
-**Recommended**: All models work well with CoreML acceleration
-
-```bash
-pip install uniface[silicon]
-```
-
-**Recommended models**:
-- **Fast**: `SCRFD(SCRFD_500M)` - Lightweight, real-time capable
-- **Balanced**: `RetinaFace(MNET_V2)` - Good accuracy/speed tradeoff
-- **Accurate**: `SCRFD(SCRFD_10G)` - High accuracy
-
-**Benchmark on your M4**: `python scripts/run_detection.py --iterations 100`
-
-#### NVIDIA GPU (CUDA)
-**Recommended**: Larger models for maximum throughput
-
-```bash
-pip install uniface[gpu]
-```
-
-**Recommended models**:
-- **Fast**: `SCRFD(SCRFD_500M)` - Maximum throughput
-- **Balanced**: `SCRFD(SCRFD_10G)` - Best overall
-- **Accurate**: `RetinaFace(RESNET34)` - Highest accuracy
-
-#### CPU Only
-**Recommended**: Lightweight models
-
-**Recommended models**:
-- **Fast**: `RetinaFace(MNET_025)` - Smallest, fastest
-- **Balanced**: `RetinaFace(MNET_V2)` - Recommended default
-- **Accurate**: `SCRFD(SCRFD_10G)` - Best accuracy on CPU
-
-**Note**: FPS values vary significantly based on image size, number of faces, and hardware. Always benchmark on your specific setup.
-
----
-
-## Benchmark Details
-
-### How to Benchmark
-
-Run benchmarks on your own hardware:
-
-```bash
-# Detection speed
-python scripts/run_detection.py --image assets/test.jpg --iterations 100
-
-# Compare models
-python scripts/run_detection.py --image assets/test.jpg --method retinaface --iterations 100
-python scripts/run_detection.py --image assets/test.jpg --method scrfd --iterations 100
-```
-
-### Accuracy Metrics Explained
-
-- **WIDER FACE**: Standard face detection benchmark with three difficulty levels
-  - **Easy**: Large faces (>50px), clear backgrounds
-  - **Medium**: Medium-sized faces (30-50px), moderate occlusion
-  - **Hard**: Small faces (<30px), heavy occlusion, blur
-
-  *Accuracy values are from the original papers - see references below*
-
-- **Model Size**: ONNX model file size (affects download time and memory)
-- **Params**: Number of model parameters (affects inference speed)
-
-### Important Notes
-
-1. **Speed varies by**:
-   - Image resolution
-   - Number of faces in image
-   - Hardware (CPU/GPU/CoreML)
-   - Batch size
-   - Operating system
-
-2. **Accuracy varies by**:
-   - Image quality
-   - Lighting conditions
-   - Face pose and occlusion
-   - Demographic factors
-
-3. **Always benchmark on your specific use case** before choosing a model
-
----
-
 ## Model Updates
 
 Models are automatically downloaded and cached on first use. Cache location: `~/.uniface/models/`
@@ -383,6 +327,8 @@ python scripts/download_model.py --model MNET_V2
 ### Model Training & Architectures
 
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) - PyTorch implementation and training code
+- **YOLOv5-Face Original**: [deepcam-cn/yolov5-face](https://github.com/deepcam-cn/yolov5-face) - Original PyTorch implementation
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) - ONNX inference implementation
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights
 
@@ -390,6 +336,6 @@ python scripts/download_model.py --model MNET_V2
 
 - **RetinaFace**: [Single-Shot Multi-Level Face Localisation in the Wild](https://arxiv.org/abs/1905.00641)
 - **SCRFD**: [Sample and Computation Redistribution for Efficient Face Detection](https://arxiv.org/abs/2105.04714)
+- **YOLOv5-Face**: [YOLO5Face: Why Reinventing a Face Detector](https://arxiv.org/abs/2105.12931)
 - **ArcFace**: [Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
 - **SphereFace**: [Deep Hypersphere Embedding for Face Recognition](https://arxiv.org/abs/1704.08063)
-

QUICKSTART.md

@@ -7,8 +7,8 @@ Get up and running with UniFace in 5 minutes! This guide covers the most common
 ## Installation
 
 ```bash
-# macOS (Apple Silicon)
-pip install uniface[silicon]
+# macOS (Apple Silicon) - automatically includes ARM64 optimizations
+pip install uniface
 
 # Linux/Windows with NVIDIA GPU
 pip install uniface[gpu]
@@ -45,6 +45,7 @@ for i, face in enumerate(faces):
 ```
 
 **Output:**
+
 ```
 Face 1:
   Confidence: 0.99
@@ -74,7 +75,13 @@ scores = [f['confidence'] for f in faces]
 landmarks = [f['landmarks'] for f in faces]
 
 # Draw on image
-draw_detections(image, bboxes, scores, landmarks, vis_threshold=0.6)
+draw_detections(
+    image=image,
+    bboxes=bboxes,
+    scores=scores,
+    landmarks=landmarks,
+    vis_threshold=0.6,
+)
 
 # Save result
 cv2.imwrite("output.jpg", image)
@@ -114,14 +121,15 @@ if faces1 and faces2:
 
     # Interpret result
     if similarity > 0.6:
-        print(f"✅ Same person (similarity: {similarity:.3f})")
+        print(f"Same person (similarity: {similarity:.3f})")
     else:
-        print(f"❌ Different people (similarity: {similarity:.3f})")
+        print(f"Different people (similarity: {similarity:.3f})")
 else:
     print("No faces detected")
 ```
 
 **Similarity thresholds:**
+
 - `> 0.6`: Same person (high confidence)
 - `0.4 - 0.6`: Uncertain (manual review)
 - `< 0.4`: Different people
@@ -154,7 +162,12 @@ while True:
     bboxes = [f['bbox'] for f in faces]
     scores = [f['confidence'] for f in faces]
     landmarks = [f['landmarks'] for f in faces]
-    draw_detections(frame, bboxes, scores, landmarks)
+    draw_detections(
+        image=frame,
+        bboxes=bboxes,
+        scores=scores,
+        landmarks=landmarks,
+    )
 
     # Show frame
     cv2.imshow("UniFace - Press 'q' to quit", frame)
@@ -187,10 +200,12 @@ faces = detector.detect(image)
 # Predict attributes
 for i, face in enumerate(faces):
     gender, age = age_gender.predict(image, face['bbox'])
-    print(f"Face {i+1}: {gender}, {age} years old")
+    gender_str = 'Female' if gender == 0 else 'Male'
+    print(f"Face {i+1}: {gender_str}, {age} years old")
 ```
 
 **Output:**
+
 ```
 Face 1: Male, 32 years old
 Face 2: Female, 28 years old
@@ -264,31 +279,53 @@ print("Done!")
 
 Choose the right model for your use case:
 
+### Detection Models
+
 ```python
-from uniface import create_detector
-from uniface.constants import RetinaFaceWeights, SCRFDWeights
+from uniface.detection import RetinaFace, SCRFD, YOLOv5Face
+from uniface.constants import RetinaFaceWeights, SCRFDWeights, YOLOv5FaceWeights
 
 # Fast detection (mobile/edge devices)
-detector = create_detector(
-    'retinaface',
+detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_025,
     conf_thresh=0.7
 )
 
 # Balanced (recommended)
-detector = create_detector(
-    'retinaface',
+detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_V2
 )
 
+# Real-time with high accuracy
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    conf_thresh=0.6,
+    nms_thresh=0.5
+)
+
 # High accuracy (server/GPU)
-detector = create_detector(
-    'scrfd',
+detector = SCRFD(
     model_name=SCRFDWeights.SCRFD_10G_KPS,
     conf_thresh=0.5
 )
 ```
 
+### Recognition Models
+
+```python
+from uniface import ArcFace, MobileFace, SphereFace
+from uniface.constants import MobileFaceWeights, SphereFaceWeights
+
+# ArcFace (recommended for most use cases)
+recognizer = ArcFace()  # Best accuracy
+
+# MobileFace (lightweight for mobile/edge)
+recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)  # Fast, small size
+
+# SphereFace (angular margin approach)
+recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)  # Alternative method
+```
+
 ---
 
 ## Common Issues
@@ -316,20 +353,22 @@ print("Available providers:", ort.get_available_providers())
 
 ### 3. Slow Performance on Mac
 
-Make sure you installed with CoreML support:
+The standard installation includes ARM64 optimizations for Apple Silicon. If performance is slow, verify you're using the ARM64 build of Python:
 
 ```bash
-pip install uniface[silicon]
+python -c "import platform; print(platform.machine())"
+# Should show: arm64 (not x86_64)
 ```
 
 ### 4. Import Errors
 
 ```python
-# ✅ Correct imports
-from uniface import RetinaFace, ArcFace, Landmark106
-from uniface.detection import create_detector
+# Correct imports
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.landmark import Landmark106
 
-# ❌ Wrong imports
+# Wrong imports
 from uniface import retinaface  # Module, not class
 ```
 
@@ -337,7 +376,20 @@ from uniface import retinaface  # Module, not class
 
 ## Next Steps
 
-- **Detailed Examples**: Check the [examples/](examples/) folder for Jupyter notebooks
+### Jupyter Notebook Examples
+
+Explore interactive examples for common tasks:
+
+| Example | Description | Notebook |
+|---------|-------------|----------|
+| **Face Detection** | Detect faces and facial landmarks | [face_detection.ipynb](examples/face_detection.ipynb) |
+| **Face Alignment** | Align and crop faces for recognition | [face_alignment.ipynb](examples/face_alignment.ipynb) |
+| **Face Recognition** | Extract face embeddings and compare faces | [face_analyzer.ipynb](examples/face_analyzer.ipynb) |
+| **Face Verification** | Compare two faces to verify identity | [face_verification.ipynb](examples/face_verification.ipynb) |
+| **Face Search** | Find a person in a group photo | [face_search.ipynb](examples/face_search.ipynb) |
+
+### Additional Resources
+
 - **Model Benchmarks**: See [MODELS.md](MODELS.md) for performance comparisons
 - **Full Documentation**: Read [README.md](README.md) for complete API reference
 
@@ -346,10 +398,6 @@ from uniface import retinaface  # Module, not class
 ## References
 
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch)
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference)
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition)
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface)
-
----
-
-Happy coding! 🚀
-

README.md

@@ -1,10 +1,11 @@
 # UniFace: All-in-One Face Analysis Library
 
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
-![Python](https://img.shields.io/badge/Python-3.10%2B-blue)
-[![PyPI Version](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
+[![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
+[![PyPI](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
 [![CI](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
 [![Downloads](https://pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
+[![DeepWiki](https://img.shields.io/badge/DeepWiki-yakhyo%2Funiface-blue.svg?logo=data:image/png;base64,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)](https://deepwiki.com/yakhyo/uniface)
 
 <div align="center">
     <img src=".github/logos/logo_web.webp" width=75%>
@@ -16,12 +17,12 @@
 
 ## Features
 
-- **High-Speed Face Detection**: ONNX-optimized RetinaFace and SCRFD models
+- **High-Speed Face Detection**: ONNX-optimized RetinaFace, SCRFD, and YOLOv5-Face models
 - **Facial Landmark Detection**: Accurate 106-point landmark localization
 - **Face Recognition**: ArcFace, MobileFace, and SphereFace embeddings
 - **Attribute Analysis**: Age, gender, and emotion detection
 - **Face Alignment**: Precise alignment for downstream tasks
-- **Hardware Acceleration**: CoreML (Apple Silicon), CUDA (NVIDIA), CPU fallback
+- **Hardware Acceleration**: ARM64 optimizations (Apple Silicon), CUDA (NVIDIA), CPU fallback
 - **Simple API**: Intuitive factory functions and clean interfaces
 - **Production-Ready**: Type hints, comprehensive logging, PEP8 compliant
 
@@ -39,31 +40,24 @@ pip install uniface
 
 #### macOS (Apple Silicon - M1/M2/M3/M4)
 
-For optimal performance with **CoreML acceleration** (3-5x faster):
+For Apple Silicon Macs, the standard installation automatically includes optimized ARM64 support:
 
 ```bash
-# Standard installation (CPU only)
 pip install uniface
-
-# With CoreML acceleration (recommended for M-series chips)
-pip install uniface[silicon]
 ```
 
-**Verify CoreML is available:**
-```python
-import onnxruntime as ort
-print(ort.get_available_providers())
-# Should show: ['CoreMLExecutionProvider', 'CPUExecutionProvider']
-```
+The base `onnxruntime` package (included with uniface) has native Apple Silicon support with ARM64 optimizations built-in since version 1.13+.
 
 #### Linux/Windows with NVIDIA GPU
 
+For CUDA acceleration on NVIDIA GPUs:
+
 ```bash
-# With CUDA acceleration
 pip install uniface[gpu]
 ```
 
 **Requirements:**
+
 - CUDA 11.x or 12.x
 - cuDNN 8.x
 - See [ONNX Runtime GPU requirements](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html)
@@ -154,7 +148,8 @@ age_gender = AgeGender()
 
 faces = detector.detect(image)
 gender, age = age_gender.predict(image, faces[0]['bbox'])
-print(f"{gender}, {age} years old")
+gender_str = 'Female' if gender == 0 else 'Male'
+print(f"{gender_str}, {age} years old")
 ```
 
 ---
@@ -172,29 +167,33 @@ print(f"{gender}, {age} years old")
 ### Factory Functions (Recommended)
 
 ```python
-from uniface import create_detector, create_recognizer, create_landmarker
+from uniface.detection import RetinaFace, SCRFD
+from uniface.recognition import ArcFace
+from uniface.landmark import Landmark106
+
+from uniface.constants import SCRFDWeights
 
 # Create detector with default settings
-detector = create_detector('retinaface')
+detector = RetinaFace()
 
 # Create with custom config
-detector = create_detector(
-    'scrfd',
-    model_name='scrfd_10g_kps',
-    conf_thresh=0.8,
+detector = SCRFD(
+    model_name=SCRFDWeights.SCRFD_10G_KPS, # SCRFDWeights.SCRFD_500M_KPS
+    conf_thresh=0.4,
     input_size=(640, 640)
 )
+# Or with defaults settings: detector = SCRFD()
 
 # Recognition and landmarks
-recognizer = create_recognizer('arcface')
-landmarker = create_landmarker('2d106det')
+recognizer = ArcFace()
+landmarker = Landmark106()
 ```
 
 ### Direct Model Instantiation
 
 ```python
-from uniface import RetinaFace, SCRFD, ArcFace, MobileFace
-from uniface.constants import RetinaFaceWeights
+from uniface import RetinaFace, SCRFD, YOLOv5Face, ArcFace, MobileFace, SphereFace
+from uniface.constants import RetinaFaceWeights, YOLOv5FaceWeights
 
 # Detection
 detector = RetinaFace(
@@ -202,10 +201,20 @@ detector = RetinaFace(
     conf_thresh=0.5,
     nms_thresh=0.4
 )
+# Or detector = RetinaFace()
+
+# YOLOv5-Face detection
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    conf_thresh=0.6,
+    nms_thresh=0.5
+)
+# Or detector = YOLOv5Face
 
 # Recognition
 recognizer = ArcFace()  # Uses default weights
 recognizer = MobileFace()  # Lightweight alternative
+recognizer = SphereFace()  # Angular softmax alternative
 ```
 
 ### High-Level Detection API
@@ -214,26 +223,56 @@ recognizer = MobileFace()  # Lightweight alternative
 from uniface import detect_faces
 
 # One-line face detection
-faces = detect_faces(image, method='retinaface', conf_thresh=0.8)
+faces = detect_faces(image, method='retinaface', conf_thresh=0.8)  # methods: retinaface, scrfd, yolov5face
 ```
 
+### Key Parameters (quick reference)
+
+**Detection**
+
+| Class          | Key params (defaults)                                                                                                                | Notes                                          |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
+| `RetinaFace` | `model_name=RetinaFaceWeights.MNET_V2`, `conf_thresh=0.5`, `nms_thresh=0.4`, `input_size=(640, 640)`, `dynamic_size=False` | Supports 5-point landmarks                     |
+| `SCRFD`      | `model_name=SCRFDWeights.SCRFD_10G_KPS`, `conf_thresh=0.5`, `nms_thresh=0.4`, `input_size=(640, 640)`                        | Supports 5-point landmarks                     |
+| `YOLOv5Face` | `model_name=YOLOv5FaceWeights.YOLOV5S`, `conf_thresh=0.6`, `nms_thresh=0.5`, `input_size=640` (fixed)                        | Supports 5-point landmarks; models: YOLOV5N/S/M; `input_size` must be 640 |
+
+**Recognition**
+
+| Class          | Key params (defaults)                     | Notes                                 |
+| -------------- | ----------------------------------------- | ------------------------------------- |
+| `ArcFace`    | `model_name=ArcFaceWeights.MNET`        | Returns 512-dim normalized embeddings |
+| `MobileFace` | `model_name=MobileFaceWeights.MNET_V2`  | Lightweight embeddings                |
+| `SphereFace` | `model_name=SphereFaceWeights.SPHERE20` | Angular softmax variant               |
+
+**Landmark & Attributes**
+
+| Class           | Key params (defaults)                                                 | Notes                                   |
+| --------------- | --------------------------------------------------------------------- | --------------------------------------- |
+| `Landmark106` | No required params                                                    | 106-point landmarks                     |
+| `AgeGender`   | `model_name=AgeGenderWeights.DEFAULT`; `input_size` auto-detected | Requires bbox; ONNXRuntime              |
+| `Emotion`     | `model_weights=DDAMFNWeights.AFFECNET7`, `input_size=(112, 112)`  | Requires 5-point landmarks; TorchScript |
+
 ---
 
 ## Model Performance
 
 ### Face Detection (WIDER FACE Dataset)
 
-| Model              | Easy   | Medium | Hard   | Use Case                |
-|--------------------|--------|--------|--------|-------------------------|
-| retinaface_mnet025 | 88.48% | 87.02% | 80.61% | Mobile/Edge devices     |
-| retinaface_mnet_v2 | 91.70% | 91.03% | 86.60% | Balanced (recommended)  |
-| retinaface_r34     | 94.16% | 93.12% | 88.90% | High accuracy           |
-| scrfd_500m         | 90.57% | 88.12% | 68.51% | Real-time applications  |
-| scrfd_10g          | 95.16% | 93.87% | 83.05% | Best accuracy/speed     |
+| Model              | Easy   | Medium | Hard   | Use Case               |
+| ------------------ | ------ | ------ | ------ | ---------------------- |
+| retinaface_mnet025 | 88.48% | 87.02% | 80.61% | Mobile/Edge devices    |
+| retinaface_mnet_v2 | 91.70% | 91.03% | 86.60% | Balanced (recommended) |
+| retinaface_r34     | 94.16% | 93.12% | 88.90% | High accuracy          |
+| scrfd_500m         | 90.57% | 88.12% | 68.51% | Real-time applications |
+| scrfd_10g          | 95.16% | 93.87% | 83.05% | Best accuracy/speed    |
+| yolov5n_face       | 93.61% | 91.52% | 80.53% | Lightweight/Mobile     |
+| yolov5s_face       | 94.33% | 92.61% | 83.15% | Real-time + accuracy   |
+| yolov5m_face       | 95.30% | 93.76% | 85.28% | High accuracy          |
 
-*Accuracy values from original papers: [RetinaFace](https://arxiv.org/abs/1905.00641), [SCRFD](https://arxiv.org/abs/2105.04714)*
+_Accuracy values from original papers: [RetinaFace](https://arxiv.org/abs/1905.00641), [SCRFD](https://arxiv.org/abs/2105.04714), [YOLOv5-Face](https://arxiv.org/abs/2105.12931)_
 
 **Benchmark on your hardware:**
+
 ```bash
 python scripts/run_detection.py --image assets/test.jpg --iterations 100
 ```
@@ -248,6 +287,18 @@ See [MODELS.md](MODELS.md) for detailed model information and selection guide.
 
 ## Examples
 
+### Jupyter Notebooks
+
+Interactive examples covering common face analysis tasks:
+
+| Example | Description | Notebook |
+|---------|-------------|----------|
+| **Face Detection** | Detect faces and facial landmarks | [face_detection.ipynb](examples/face_detection.ipynb) |
+| **Face Alignment** | Align and crop faces for recognition | [face_alignment.ipynb](examples/face_alignment.ipynb) |
+| **Face Recognition** | Extract face embeddings and compare faces | [face_analyzer.ipynb](examples/face_analyzer.ipynb) |
+| **Face Verification** | Compare two faces to verify identity | [face_verification.ipynb](examples/face_verification.ipynb) |
+| **Face Search** | Find a person in a group photo | [face_search.ipynb](examples/face_search.ipynb) |
+
 ### Webcam Face Detection
 
 ```python
@@ -270,7 +321,13 @@ while True:
     scores = [f['confidence'] for f in faces]
     landmarks = [f['landmarks'] for f in faces]
 
-    draw_detections(frame, bboxes, scores, landmarks, vis_threshold=0.6)
+    draw_detections(
+        image=frame,
+        bboxes=bboxes,
+        scores=scores,
+        landmarks=landmarks,
+        vis_threshold=0.6,
+    )
 
     cv2.imshow("Face Detection", frame)
     if cv2.waitKey(1) & 0xFF == ord('q'):
@@ -400,12 +457,29 @@ pip install -e ".[dev]"
 
 # Run tests
 pytest
-
-# Format code
-black uniface/
-isort uniface/
 ```
 
+### Code Formatting
+
+This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formatting.
+
+```bash
+# Format code
+ruff format .
+
+# Check for linting errors
+ruff check .
+
+# Auto-fix linting errors
+ruff check . --fix
+```
+
+Ruff configuration is in `pyproject.toml`. Key settings:
+
+- Line length: 120
+- Python target: 3.10+
+- Import sorting: `uniface` as first-party
+
 ### Project Structure
 
 ```
@@ -427,21 +501,11 @@ uniface/
 
 ## References
 
-### Model Training & Architectures
-
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) - PyTorch implementation and training code
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) - ONNX inference implementation
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights
 
-### Papers
-
-- **RetinaFace**: [Single-Shot Multi-Level Face Localisation in the Wild](https://arxiv.org/abs/1905.00641)
-- **SCRFD**: [Sample and Computation Redistribution for Efficient Face Detection](https://arxiv.org/abs/2105.04714)
-- **ArcFace**: [Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
-
----
-
 ## Contributing
 
 Contributions are welcome! Please open an issue or submit a pull request on [GitHub](https://github.com/yakhyo/uniface).
-

pyproject.toml

@@ -1,12 +1,41 @@
 [project]
 name = "uniface"
-version = "0.1.9"
+version = "1.3.2"
 description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection"
 readme = "README.md"
 license = { text = "MIT" }
-authors = [
-    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }
+authors = [{ name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }]
+maintainers = [
+    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" },
 ]
+
+requires-python = ">=3.10,<3.14"
+keywords = [
+    "face-detection",
+    "face-recognition",
+    "facial-landmarks",
+    "age-detection",
+    "gender-detection",
+    "computer-vision",
+    "deep-learning",
+    "onnx",
+    "onnxruntime",
+    "face-analysis",
+]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
 dependencies = [
     "numpy>=1.21.0",
     "opencv-python>=4.5.0",
@@ -14,25 +43,56 @@ dependencies = [
     "onnxruntime>=1.16.0",
     "scikit-image>=0.19.0",
     "requests>=2.28.0",
-    "tqdm>=4.64.0"
+    "tqdm>=4.64.0",
 ]
-requires-python = ">=3.10"
 
 [project.optional-dependencies]
-dev = ["pytest>=7.0.0"]
+dev = ["pytest>=7.0.0", "ruff>=0.4.0"]
 gpu = ["onnxruntime-gpu>=1.16.0"]
-silicon = ["onnxruntime-silicon>=1.16.0"]
 
 [project.urls]
 Homepage = "https://github.com/yakhyo/uniface"
 Repository = "https://github.com/yakhyo/uniface"
+Documentation = "https://github.com/yakhyo/uniface/blob/main/README.md"
+"Quick Start" = "https://github.com/yakhyo/uniface/blob/main/QUICKSTART.md"
+"Model Zoo" = "https://github.com/yakhyo/uniface/blob/main/MODELS.md"
 
 [build-system]
 requires = ["setuptools>=64", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
-packages = { find = {} }
+packages = { find = { where = ["."], include = ["uniface*"] } }
 
 [tool.setuptools.package-data]
-"uniface" = ["*.txt", "*.md"]
+uniface = ["py.typed"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+exclude = [
+    ".git",
+    ".ruff_cache",
+    "__pycache__",
+    "build",
+    "dist",
+    "*.egg-info",
+    ".venv",
+    "venv",
+    ".pytest_cache",
+    ".mypy_cache",
+    "*.ipynb",
+]
+
+[tool.ruff.format]
+quote-style = "single"
+
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W"]
+
+[tool.ruff.lint.flake8-quotes]
+docstring-quotes = "double"
+
+[tool.ruff.lint.isort]
+known-first-party = ["uniface"]

scripts/README.md

@@ -1,18 +1,74 @@
-### `download_model.py`
+# Scripts
 
-# Download all models
+Scripts for testing UniFace features.
+
+## Available Scripts
+
+| Script | Description |
+|--------|-------------|
+| `run_detection.py` | Face detection on image or webcam |
+| `run_age_gender.py` | Age and gender prediction |
+| `run_emotion.py` | Emotion detection (7 or 8 emotions) |
+| `run_landmarks.py` | 106-point facial landmark detection |
+| `run_recognition.py` | Face embedding extraction and comparison |
+| `run_face_analyzer.py` | Complete face analysis (detection + recognition + attributes) |
+| `run_face_search.py` | Real-time face matching against reference |
+| `run_video_detection.py` | Face detection on video files |
+| `batch_process.py` | Batch process folder of images |
+| `download_model.py` | Download model weights |
+| `sha256_generate.py` | Generate SHA256 hash for model files |
+
+## Usage Examples
 
 ```bash
-python scripts/download_model.py
+# Face detection
+python scripts/run_detection.py --image assets/test.jpg
+python scripts/run_detection.py --webcam
+
+# Age and gender
+python scripts/run_age_gender.py --image assets/test.jpg
+python scripts/run_age_gender.py --webcam
+
+# Emotion detection
+python scripts/run_emotion.py --image assets/test.jpg
+python scripts/run_emotion.py --webcam
+
+# Landmarks
+python scripts/run_landmarks.py --image assets/test.jpg
+python scripts/run_landmarks.py --webcam
+
+# Face recognition (extract embedding)
+python scripts/run_recognition.py --image assets/test.jpg
+
+# Face comparison
+python scripts/run_recognition.py --image1 face1.jpg --image2 face2.jpg
+
+# Face search (match webcam against reference)
+python scripts/run_face_search.py --image reference.jpg
+
+# Video processing
+python scripts/run_video_detection.py --input video.mp4 --output output.mp4
+
+# Batch processing
+python scripts/batch_process.py --input images/ --output results/
+
+# Download models
+python scripts/download_model.py --model-type retinaface
+python scripts/download_model.py  # downloads all
 ```
 
-# Download just RESNET18
+## Common Options
+
+| Option | Description |
+|--------|-------------|
+| `--image` | Path to input image |
+| `--webcam` | Use webcam instead of image |
+| `--method` | Choose detector: `retinaface`, `scrfd`, `yolov5face` |
+| `--threshold` | Visualization confidence threshold (default: 0.25) |
+| `--save_dir` | Output directory (default: `outputs`) |
+
+## Quick Test
 
 ```bash
-python scripts/download_model.py --model RESNET18
+python scripts/run_detection.py --image assets/test.jpg
 ```
-
-### `run_inference.py`
-```bash
-python scripts/run_inference.py --image assets/test.jpg --model MNET_V2 --iterations 10
-```

scripts/TESTING.md

@@ -1,389 +0,0 @@
-# Testing Scripts Guide
-
-Complete guide to testing all scripts in the `scripts/` directory.
-
----
-
-## 📁 Available Scripts
-
-1. **download_model.py** - Download and verify model weights
-2. **run_detection.py** - Face detection on images
-3. **run_recognition.py** - Face recognition (extract embeddings)
-4. **run_face_search.py** - Real-time face matching with webcam
-5. **sha256_generate.py** - Generate SHA256 checksums for models
-
----
-
-## Testing Each Script
-
-### 1. Test Model Download
-
-```bash
-# Download a specific model
-python scripts/download_model.py --model MNET_V2
-
-# Download all RetinaFace models (takes ~5 minutes, ~200MB)
-python scripts/download_model.py
-
-# Verify models are cached
-ls -lh ~/.uniface/models/
-```
-
-**Expected Output:**
-```
-📥 Downloading model: retinaface_mnet_v2
-2025-11-08 00:00:00 - INFO - Downloading model 'RetinaFaceWeights.MNET_V2' from https://...
-Downloading ~/.uniface/models/retinaface_mnet_v2.onnx: 100%|████| 3.5M/3.5M
-2025-11-08 00:00:05 - INFO - Successfully downloaded 'RetinaFaceWeights.MNET_V2'
-✅ All requested weights are ready and verified.
-```
-
----
-
-### 2. Test Face Detection
-
-```bash
-# Basic detection
-python scripts/run_detection.py --image assets/test.jpg
-
-# With custom settings
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --method scrfd \
-    --threshold 0.7 \
-    --save_dir outputs
-
-# Benchmark mode (100 iterations)
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --iterations 100
-```
-
-**Expected Output:**
-```
-Initializing detector: retinaface
-2025-11-08 00:00:00 - INFO - Initializing RetinaFace with model=RetinaFaceWeights.MNET_V2...
-2025-11-08 00:00:01 - INFO - CoreML acceleration enabled (Apple Silicon)
-✅ Output saved at: outputs/test_out.jpg
-[1/1] ⏱️ Inference time: 0.0234 seconds
-```
-
-**Verify Output:**
-```bash
-# Check output image was created
-ls -lh outputs/test_out.jpg
-
-# View the image (macOS)
-open outputs/test_out.jpg
-```
-
----
-
-### 3. Test Face Recognition (Embedding Extraction)
-
-```bash
-# Extract embeddings from an image
-python scripts/run_recognition.py --image assets/test.jpg
-
-# With different models
-python scripts/run_recognition.py \
-    --image assets/test.jpg \
-    --detector scrfd \
-    --recognizer mobileface
-```
-
-**Expected Output:**
-```
-Initializing detector: retinaface
-Initializing recognizer: arcface
-2025-11-08 00:00:00 - INFO - Successfully initialized face encoder from ~/.uniface/models/w600k_mbf.onnx
-Detected 1 face(s). Extracting embeddings for the first face...
-  - Embedding shape: (1, 512)
-  - L2 norm of unnormalized embedding: 64.2341
-  - L2 norm of normalized embedding: 1.0000
-```
-
----
-
-### 4. Test Real-Time Face Search (Webcam)
-
-**Prerequisites:**
-- Webcam connected
-- Reference image with a clear face
-
-```bash
-# Basic usage
-python scripts/run_face_search.py --image assets/test.jpg
-
-# With custom models
-python scripts/run_face_search.py \
-    --image assets/test.jpg \
-    --detector scrfd \
-    --recognizer arcface
-```
-
-**Expected Behavior:**
-1. Webcam window opens
-2. Faces are detected in real-time
-3. Green box = Match (similarity > 0.4)
-4. Red box = Unknown (similarity < 0.4)
-5. Press 'q' to quit
-
-**Expected Output:**
-```
-Initializing models...
-2025-11-08 00:00:00 - INFO - CoreML acceleration enabled (Apple Silicon)
-Extracting reference embedding...
-Webcam started. Press 'q' to quit.
-```
-
-**Troubleshooting:**
-```bash
-# If webcam doesn't open
-python -c "import cv2; cap = cv2.VideoCapture(0); print('Webcam OK' if cap.isOpened() else 'Webcam FAIL')"
-
-# If no faces detected
-# - Ensure good lighting
-# - Face should be frontal and clearly visible
-# - Try lowering threshold: edit script line 29, change 0.4 to 0.3
-```
-
----
-
-### 5. Test SHA256 Generator (For Developers)
-
-```bash
-# Generate checksum for a model file
-python scripts/sha256_generate.py ~/.uniface/models/retinaface_mnet_v2.onnx
-
-# Generate for all models
-for model in ~/.uniface/models/*.onnx; do
-    python scripts/sha256_generate.py "$model"
-done
-```
-
----
-
-## 🔍 Quick Verification Tests
-
-### Test 1: Imports Work
-
-```bash
-python -c "
-from uniface.detection import create_detector
-from uniface.recognition import create_recognizer
-print('✅ Imports successful')
-"
-```
-
-### Test 2: Models Download
-
-```bash
-python -c "
-from uniface import RetinaFace
-detector = RetinaFace()
-print('✅ Model downloaded and loaded')
-"
-```
-
-### Test 3: Detection Works
-
-```bash
-python -c "
-import cv2
-import numpy as np
-from uniface import RetinaFace
-
-detector = RetinaFace()
-image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-faces = detector.detect(image)
-print(f'✅ Detection works, found {len(faces)} faces')
-"
-```
-
-### Test 4: Recognition Works
-
-```bash
-python -c "
-import cv2
-import numpy as np
-from uniface import RetinaFace, ArcFace
-
-detector = RetinaFace()
-recognizer = ArcFace()
-image = cv2.imread('assets/test.jpg')
-faces = detector.detect(image)
-if faces:
-    landmarks = np.array(faces[0]['landmarks'])
-    embedding = recognizer.get_normalized_embedding(image, landmarks)
-    print(f'✅ Recognition works, embedding shape: {embedding.shape}')
-else:
-    print('⚠️ No faces detected in test image')
-"
-```
-
----
-
-## End-to-End Test Workflow
-
-Run this complete workflow to verify everything works:
-
-```bash
-#!/bin/bash
-# Save as test_all_scripts.sh
-
-echo "=== Testing UniFace Scripts ==="
-echo ""
-
-# Test 1: Download models
-echo "1️⃣ Testing model download..."
-python scripts/download_model.py --model MNET_V2
-if [ $? -eq 0 ]; then
-    echo "✅ Model download: PASS"
-else
-    echo "❌ Model download: FAIL"
-    exit 1
-fi
-echo ""
-
-# Test 2: Face detection
-echo "2️⃣ Testing face detection..."
-python scripts/run_detection.py --image assets/test.jpg --save_dir /tmp/uniface_test
-if [ $? -eq 0 ] && [ -f /tmp/uniface_test/test_out.jpg ]; then
-    echo "✅ Face detection: PASS"
-else
-    echo "❌ Face detection: FAIL"
-    exit 1
-fi
-echo ""
-
-# Test 3: Face recognition
-echo "3️⃣ Testing face recognition..."
-python scripts/run_recognition.py --image assets/test.jpg > /tmp/uniface_recognition.log
-if [ $? -eq 0 ] && grep -q "Embedding shape" /tmp/uniface_recognition.log; then
-    echo "✅ Face recognition: PASS"
-else
-    echo "❌ Face recognition: FAIL"
-    exit 1
-fi
-echo ""
-
-echo "=== All Tests Passed! 🎉 ==="
-```
-
-**Run the test suite:**
-```bash
-chmod +x test_all_scripts.sh
-./test_all_scripts.sh
-```
-
----
-
-## Performance Benchmarking
-
-### Benchmark Detection Speed
-
-```bash
-# Test different models
-for model in retinaface scrfd; do
-    echo "Testing $model..."
-    python scripts/run_detection.py \
-        --image assets/test.jpg \
-        --method $model \
-        --iterations 50
-done
-```
-
-### Benchmark Recognition Speed
-
-```bash
-# Test different recognizers
-for recognizer in arcface mobileface; do
-    echo "Testing $recognizer..."
-    time python scripts/run_recognition.py \
-        --image assets/test.jpg \
-        --recognizer $recognizer
-done
-```
-
----
-
-## 🐛 Common Issues
-
-### Issue: "No module named 'uniface'"
-
-```bash
-# Solution: Install in editable mode
-pip install -e .
-```
-
-### Issue: "Failed to load image"
-
-```bash
-# Check image exists
-ls -lh assets/test.jpg
-
-# Try with absolute path
-python scripts/run_detection.py --image $(pwd)/assets/test.jpg
-```
-
-### Issue: "No faces detected"
-
-```bash
-# Lower confidence threshold
-python scripts/run_detection.py \
-    --image assets/test.jpg \
-    --threshold 0.3
-```
-
-### Issue: Models downloading slowly
-
-```bash
-# Check internet connection
-curl -I https://github.com/yakhyo/uniface/releases
-
-# Or download manually
-wget https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv2.onnx \
-    -O ~/.uniface/models/retinaface_mnet_v2.onnx
-```
-
-### Issue: CoreML not available on Mac
-
-```bash
-# Install CoreML-enabled ONNX Runtime
-pip uninstall onnxruntime
-pip install onnxruntime-silicon
-
-# Verify
-python -c "import onnxruntime as ort; print(ort.get_available_providers())"
-# Should show: ['CoreMLExecutionProvider', 'CPUExecutionProvider']
-```
-
----
-
-## ✅ Script Status Summary
-
-| Script                | Status | API Updated | Tested |
-|-----------------------|--------|-------------|--------|
-| download_model.py     | ✅     | ✅          | ✅     |
-| run_detection.py      | ✅     | ✅          | ✅     |
-| run_recognition.py    | ✅     | ✅          | ✅     |
-| run_face_search.py    | ✅     | ✅          | ✅     |
-| sha256_generate.py    | ✅     | N/A         | ✅     |
-
-All scripts are updated and working with the new dict-based API! 🎉
-
----
-
-## 📝 Notes
-
-- All scripts now use the factory functions (`create_detector`, `create_recognizer`)
-- Scripts work with the new dict-based detection API
-- Model download bug is fixed (enum vs string issue)
-- CoreML acceleration is automatically detected on Apple Silicon
-- All scripts include proper error handling
-
----
-
-Need help with a specific script? Check the main [README.md](../README.md) or [QUICKSTART.md](../QUICKSTART.md)!
-

scripts/batch_process.py

@@ -0,0 +1,98 @@
+# Batch face detection on a folder of images
+# Usage: python batch_process.py --input images/ --output results/
+
+import argparse
+from pathlib import Path
+
+import cv2
+from tqdm import tqdm
+
+from uniface import SCRFD, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def get_image_files(input_dir: Path, extensions: tuple) -> list:
+    files = []
+    for ext in extensions:
+        files.extend(input_dir.glob(f'*.{ext}'))
+        files.extend(input_dir.glob(f'*.{ext.upper()}'))
+    return sorted(files)
+
+
+def process_image(detector, image_path: Path, output_path: Path, threshold: float) -> int:
+    """Process single image. Returns face count or -1 on error."""
+    image = cv2.imread(str(image_path))
+    if image is None:
+        return -1
+
+    faces = detector.detect(image)
+
+    # unpack face data for visualization
+    bboxes = [f['bbox'] for f in faces]
+    scores = [f['confidence'] for f in faces]
+    landmarks = [f['landmarks'] for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    cv2.putText(
+        image,
+        f'Faces: {len(faces)}',
+        (10, 30),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        1,
+        (0, 255, 0),
+        2,
+    )
+    cv2.imwrite(str(output_path), image)
+
+    return len(faces)
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Batch process images with face detection')
+    parser.add_argument('--input', type=str, required=True, help='Input directory')
+    parser.add_argument('--output', type=str, required=True, help='Output directory')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--extensions', type=str, default='jpg,jpeg,png,bmp', help='Image extensions')
+    args = parser.parse_args()
+
+    input_path = Path(args.input)
+    output_path = Path(args.output)
+
+    if not input_path.exists():
+        print(f"Error: Input directory '{args.input}' does not exist")
+        return
+
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    extensions = tuple(ext.strip() for ext in args.extensions.split(','))
+    image_files = get_image_files(input_path, extensions)
+
+    if not image_files:
+        print(f'No images found with extensions {extensions}')
+        return
+
+    print(f'Found {len(image_files)} images')
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+
+    success, errors, total_faces = 0, 0, 0
+
+    for img_path in tqdm(image_files, desc='Processing', unit='img'):
+        out_path = output_path / f'{img_path.stem}_detected{img_path.suffix}'
+        result = process_image(detector, img_path, out_path, args.threshold)
+
+        if result >= 0:
+            success += 1
+            total_faces += result
+        else:
+            errors += 1
+            print(f'\nFailed: {img_path.name}')
+
+    print(f'\nDone! {success} processed, {errors} errors, {total_faces} faces total')
+
+
+if __name__ == '__main__':
+    main()

scripts/download_model.py

@@ -1,31 +1,60 @@
 import argparse
-from uniface.constants import RetinaFaceWeights
+
+from uniface.constants import (
+    AgeGenderWeights,
+    ArcFaceWeights,
+    DDAMFNWeights,
+    LandmarkWeights,
+    MobileFaceWeights,
+    RetinaFaceWeights,
+    SCRFDWeights,
+    SphereFaceWeights,
+)
 from uniface.model_store import verify_model_weights
 
+MODEL_TYPES = {
+    'retinaface': RetinaFaceWeights,
+    'sphereface': SphereFaceWeights,
+    'mobileface': MobileFaceWeights,
+    'arcface': ArcFaceWeights,
+    'scrfd': SCRFDWeights,
+    'ddamfn': DDAMFNWeights,
+    'agegender': AgeGenderWeights,
+    'landmark': LandmarkWeights,
+}
+
+
+def download_models(model_enum):
+    for weight in model_enum:
+        print(f'Downloading: {weight.value}')
+        try:
+            verify_model_weights(weight)
+            print(f'  Done: {weight.value}')
+        except Exception as e:
+            print(f'  Failed: {e}')
+
 
 def main():
-    parser = argparse.ArgumentParser(description="Download and verify RetinaFace model weights.")
+    parser = argparse.ArgumentParser(description='Download model weights')
     parser.add_argument(
-        "--model",
+        '--model-type',
         type=str,
-        choices=[m.name for m in RetinaFaceWeights],
-        help="Model to download (e.g. MNET_V2). If not specified, all models will be downloaded.",
+        choices=list(MODEL_TYPES.keys()),
+        help='Model type to download. If not specified, downloads all.',
     )
     args = parser.parse_args()
 
-    if args.model:
-        weight = RetinaFaceWeights[args.model]
-        print(f"📥 Downloading model: {weight.value}")
-        verify_model_weights(weight)  # Pass enum, not string
+    if args.model_type:
+        print(f'Downloading {args.model_type} models...')
+        download_models(MODEL_TYPES[args.model_type])
     else:
-        print("📥 Downloading all models...")
-        for weight in RetinaFaceWeights:
-            verify_model_weights(weight)  # Pass enum, not string
+        print('Downloading all models...')
+        for name, model_enum in MODEL_TYPES.items():
+            print(f'\n{name}:')
+            download_models(model_enum)
 
-    print("✅ All requested weights are ready and verified.")
+    print('\nDone!')
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     main()
-
-

scripts/run_age_gender.py

@@ -0,0 +1,128 @@
+# Age and gender prediction on detected faces
+# Usage: python run_age_gender.py --image path/to/image.jpg
+#        python run_age_gender.py --webcam
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, AgeGender, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def draw_age_gender_label(image, bbox, gender_id: int, age: int):
+    """Draw age/gender label above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    gender_str = 'Female' if gender_id == 0 else 'Male'
+    text = f'{gender_str}, {age}y'
+    (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), (0, 255, 0), -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+
+def process_image(
+    detector,
+    age_gender,
+    image_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    bboxes = [f['bbox'] for f in faces]
+    scores = [f['confidence'] for f in faces]
+    landmarks = [f['landmarks'] for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    for i, face in enumerate(faces):
+        gender_id, age = age_gender.predict(image, face['bbox'])
+        gender_str = 'Female' if gender_id == 0 else 'Male'
+        print(f'  Face {i + 1}: {gender_str}, {age} years old')
+        draw_age_gender_label(image, face['bbox'], gender_id, age)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_age_gender.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def run_webcam(detector, age_gender, threshold: float = 0.6):
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
+    if not cap.isOpened():
+        print('Cannot open webcam')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        # unpack face data for visualization
+        bboxes = [f['bbox'] for f in faces]
+        scores = [f['confidence'] for f in faces]
+        landmarks = [f['landmarks'] for f in faces]
+        draw_detections(frame, bboxes, scores, landmarks, vis_threshold=threshold)
+
+        for face in faces:
+            gender_id, age = age_gender.predict(frame, face['bbox'])  # predict per face
+            draw_age_gender_label(frame, face['bbox'], gender_id, age)
+
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow('Age & Gender Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run age and gender detection')
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--webcam', action='store_true', help='Use webcam')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--save_dir', type=str, default='outputs')
+    args = parser.parse_args()
+
+    if not args.image and not args.webcam:
+        parser.error('Either --image or --webcam must be specified')
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    age_gender = AgeGender()
+
+    if args.webcam:
+        run_webcam(detector, age_gender, args.threshold)
+    else:
+        process_image(detector, age_gender, args.image, args.save_dir, args.threshold)
+
+
+if __name__ == '__main__':
+    main()

scripts/run_detection.py

@@ -1,87 +1,110 @@
-import os
-import cv2
-import time
-import argparse
-import numpy as np
+# Face detection on image or webcam
+# Usage: python run_detection.py --image path/to/image.jpg
+#        python run_detection.py --webcam
 
-# UPDATED: Use the factory function and import from the new location
-from uniface.detection import create_detector
+import argparse
+import os
+
+import cv2
+
+from uniface.detection import SCRFD, RetinaFace, YOLOv5Face
 from uniface.visualization import draw_detections
 
 
-def run_inference(detector, image_path: str, vis_threshold: float = 0.6, save_dir: str = "outputs"):
-    """
-    Run face detection on a single image.
-
-    Args:
-        detector: Initialized face detector.
-        image_path (str): Path to input image.
-        vis_threshold (float): Threshold for drawing detections.
-        save_dir (str): Directory to save output image.
-    """
+def process_image(detector, image_path: str, threshold: float = 0.6, save_dir: str = 'outputs'):
     image = cv2.imread(image_path)
     if image is None:
-        print(f"❌ Error: Failed to load image from '{image_path}'")
+        print(f"Error: Failed to load image from '{image_path}'")
         return
 
-    # 1. Get the list of face dictionaries from the detector
     faces = detector.detect(image)
 
     if faces:
-        # 2. Unpack the data into separate lists
         bboxes = [face['bbox'] for face in faces]
         scores = [face['confidence'] for face in faces]
         landmarks = [face['landmarks'] for face in faces]
-
-        # 3. Pass the unpacked lists to the drawing function
-        draw_detections(image, bboxes, scores, landmarks, vis_threshold=0.6)
-
+        draw_detections(image, bboxes, scores, landmarks, vis_threshold=threshold)
 
     os.makedirs(save_dir, exist_ok=True)
-    output_path = os.path.join(save_dir, f"{os.path.splitext(os.path.basename(image_path))[0]}_out.jpg")
+    output_path = os.path.join(save_dir, f'{os.path.splitext(os.path.basename(image_path))[0]}_out.jpg')
     cv2.imwrite(output_path, image)
-    print(f"✅ Output saved at: {output_path}")
+    print(f'Output saved: {output_path}')
+
+
+def run_webcam(detector, threshold: float = 0.6):
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
+    if not cap.isOpened():
+        print('Cannot open webcam')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        # unpack face data for visualization
+        bboxes = [f['bbox'] for f in faces]
+        scores = [f['confidence'] for f in faces]
+        landmarks = [f['landmarks'] for f in faces]
+        draw_detections(
+            image=frame,
+            bboxes=bboxes,
+            scores=scores,
+            landmarks=landmarks,
+            vis_threshold=threshold,
+            draw_score=True,
+            fancy_bbox=True,
+        )
+
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow('Face Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Run face detection on an image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the input image")
-    parser.add_argument(
-        "--method",
-        type=str,
-        default="retinaface",
-        choices=['retinaface', 'scrfd'],
-        help="Detection method to use."
-    )
-    parser.add_argument("--threshold", type=float, default=0.6, help="Visualization confidence threshold")
-    parser.add_argument("--iterations", type=int, default=1, help="Number of inference runs for benchmarking")
-    parser.add_argument("--save_dir", type=str, default="outputs", help="Directory to save output images")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
+    parser = argparse.ArgumentParser(description='Run face detection')
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--webcam', action='store_true', help='Use webcam')
+    parser.add_argument('--method', type=str, default='retinaface', choices=['retinaface', 'scrfd', 'yolov5face'])
+    parser.add_argument('--threshold', type=float, default=0.25, help='Visualization threshold')
+    parser.add_argument('--save_dir', type=str, default='outputs')
     args = parser.parse_args()
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
+    if not args.image and not args.webcam:
+        parser.error('Either --image or --webcam must be specified')
 
-    print(f"Initializing detector: {args.method}")
-    detector = create_detector(method=args.method)
+    if args.method == 'retinaface':
+        detector = RetinaFace()
+    elif args.method == 'scrfd':
+        detector = SCRFD()
+    else:
+        from uniface.constants import YOLOv5FaceWeights
 
-    avg_time = 0
-    for i in range(args.iterations):
-        start = time.time()
-        run_inference(detector, args.image, args.threshold, args.save_dir)
-        elapsed = time.time() - start
-        print(f"[{i + 1}/{args.iterations}] ⏱️ Inference time: {elapsed:.4f} seconds")
-        if i >= 0:  # Avoid counting the first run if it includes model loading time
-            avg_time += elapsed
+        detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5N)
 
-    if args.iterations > 1:
-        # Adjust average calculation to exclude potential first-run overhead
-        effective_iterations = max(1, args.iterations)
-        print(
-            f"\n🔥 Average inference time over {effective_iterations} runs: {avg_time / effective_iterations:.4f} seconds")
+    if args.webcam:
+        run_webcam(detector, args.threshold)
+    else:
+        process_image(detector, args.image, args.threshold, args.save_dir)
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     main()

scripts/run_emotion.py

@@ -0,0 +1,126 @@
+# Emotion detection on detected faces
+# Usage: python run_emotion.py --image path/to/image.jpg
+#        python run_emotion.py --webcam
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, Emotion, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def draw_emotion_label(image, bbox, emotion: str, confidence: float):
+    """Draw emotion label above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    text = f'{emotion} ({confidence:.2f})'
+    (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), (255, 0, 0), -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
+
+
+def process_image(
+    detector,
+    emotion_predictor,
+    image_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    bboxes = [f['bbox'] for f in faces]
+    scores = [f['confidence'] for f in faces]
+    landmarks = [f['landmarks'] for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    for i, face in enumerate(faces):
+        emotion, confidence = emotion_predictor.predict(image, face['landmarks'])
+        print(f'  Face {i + 1}: {emotion} (confidence: {confidence:.3f})')
+        draw_emotion_label(image, face['bbox'], emotion, confidence)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_emotion.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def run_webcam(detector, emotion_predictor, threshold: float = 0.6):
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
+    if not cap.isOpened():
+        print('Cannot open webcam')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        # unpack face data for visualization
+        bboxes = [f['bbox'] for f in faces]
+        scores = [f['confidence'] for f in faces]
+        landmarks = [f['landmarks'] for f in faces]
+        draw_detections(frame, bboxes, scores, landmarks, vis_threshold=threshold)
+
+        for face in faces:
+            emotion, confidence = emotion_predictor.predict(frame, face['landmarks'])
+            draw_emotion_label(frame, face['bbox'], emotion, confidence)
+
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow('Emotion Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run emotion detection')
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--webcam', action='store_true', help='Use webcam')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--save_dir', type=str, default='outputs')
+    args = parser.parse_args()
+
+    if not args.image and not args.webcam:
+        parser.error('Either --image or --webcam must be specified')
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    emotion_predictor = Emotion()
+
+    if args.webcam:
+        run_webcam(detector, emotion_predictor, args.threshold)
+    else:
+        process_image(detector, emotion_predictor, args.image, args.save_dir, args.threshold)
+
+
+if __name__ == '__main__':
+    main()

scripts/run_face_analyzer.py

@@ -0,0 +1,116 @@
+# Face analysis using FaceAnalyzer
+# Usage: python run_face_analyzer.py --image path/to/image.jpg
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import AgeGender, ArcFace, FaceAnalyzer, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def draw_face_info(image, face, face_id):
+    """Draw face ID and attributes above bounding box."""
+    x1, y1, x2, y2 = map(int, face.bbox)
+    lines = [f'ID: {face_id}', f'Conf: {face.confidence:.2f}']
+    if face.age and face.sex:
+        lines.append(f'{face.sex}, {face.age}y')
+
+    for i, line in enumerate(lines):
+        y_pos = y1 - 10 - (len(lines) - 1 - i) * 25
+        if y_pos < 20:
+            y_pos = y2 + 20 + i * 25
+        (tw, th), _ = cv2.getTextSize(line, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+        cv2.rectangle(image, (x1, y_pos - th - 5), (x1 + tw + 10, y_pos + 5), (0, 255, 0), -1)
+        cv2.putText(image, line, (x1 + 5, y_pos), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+
+def process_image(analyzer, image_path: str, save_dir: str = 'outputs', show_similarity: bool = True):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = analyzer.analyze(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    for i, face in enumerate(faces, 1):
+        info = f'  Face {i}: {face.sex}, {face.age}y' if face.age and face.sex else f'  Face {i}'
+        if face.embedding is not None:
+            info += f' (embedding: {face.embedding.shape})'
+        print(info)
+
+    if show_similarity and len(faces) >= 2:
+        print('\nSimilarity Matrix:')
+        n = len(faces)
+        sim_matrix = np.zeros((n, n))
+
+        for i in range(n):
+            for j in range(i, n):
+                if i == j:
+                    sim_matrix[i][j] = 1.0
+                else:
+                    sim = faces[i].compute_similarity(faces[j])
+                    sim_matrix[i][j] = sim
+                    sim_matrix[j][i] = sim
+
+        print('     ', end='')
+        for i in range(n):
+            print(f'  F{i + 1:2d}  ', end='')
+        print('\n     ' + '-' * (7 * n))
+
+        for i in range(n):
+            print(f'F{i + 1:2d} | ', end='')
+            for j in range(n):
+                print(f'{sim_matrix[i][j]:6.3f} ', end='')
+            print()
+
+        pairs = [(i, j, sim_matrix[i][j]) for i in range(n) for j in range(i + 1, n)]
+        pairs.sort(key=lambda x: x[2], reverse=True)
+
+        print('\nTop matches (>0.4 = same person):')
+        for i, j, sim in pairs[:3]:
+            status = 'Same' if sim > 0.4 else 'Different'
+            print(f'  Face {i + 1} ↔ Face {j + 1}: {sim:.3f} ({status})')
+
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+
+    for i, face in enumerate(faces, 1):
+        draw_face_info(image, face, i)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_analysis.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face analysis with detection, recognition, and attributes')
+    parser.add_argument('--image', type=str, required=True, help='Path to input image')
+    parser.add_argument('--save_dir', type=str, default='outputs', help='Output directory')
+    parser.add_argument('--no-similarity', action='store_true', help='Skip similarity matrix computation')
+    args = parser.parse_args()
+
+    if not os.path.exists(args.image):
+        print(f'Error: Image not found: {args.image}')
+        return
+
+    detector = RetinaFace()
+    recognizer = ArcFace()
+    age_gender = AgeGender()
+    analyzer = FaceAnalyzer(detector, recognizer, age_gender)
+
+    process_image(analyzer, args.image, args.save_dir, show_similarity=not args.no_similarity)
+
+
+if __name__ == '__main__':
+    main()

scripts/run_face_search.py

@@ -1,68 +1,70 @@
+# Real-time face search: match webcam faces against a reference image
+# Usage: python run_face_search.py --image reference.jpg
+
 import argparse
 
 import cv2
 import numpy as np
 
-# Use the new high-level factory functions
-from uniface.detection import create_detector
+from uniface.detection import SCRFD, RetinaFace
 from uniface.face_utils import compute_similarity
-from uniface.recognition import create_recognizer
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+def get_recognizer(name: str):
+    if name == 'arcface':
+        return ArcFace()
+    elif name == 'mobileface':
+        return MobileFace()
+    else:
+        return SphereFace()
 
 
 def extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
-    """Extracts a normalized embedding from the first face found in an image."""
     image = cv2.imread(image_path)
     if image is None:
-        raise RuntimeError(f"Failed to load image: {image_path}")
+        raise RuntimeError(f'Failed to load image: {image_path}')
 
     faces = detector.detect(image)
     if not faces:
-        raise RuntimeError("No faces found in reference image.")
+        raise RuntimeError('No faces found in reference image.')
 
-    # Get landmarks from the first detected face dictionary
-    landmarks = np.array(faces[0]["landmarks"])
-
-    # Use normalized embedding for more reliable similarity comparison
-    embedding = recognizer.get_normalized_embedding(image, landmarks)
-    return embedding
+    landmarks = faces[0]['landmarks']
+    return recognizer.get_normalized_embedding(image, landmarks)
 
 
-def run_video(detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
-    """Run real-time face recognition from a webcam feed."""
-    cap = cv2.VideoCapture(0)
+def run_webcam(detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
     if not cap.isOpened():
-        raise RuntimeError("Webcam could not be opened.")
-    print("Webcam started. Press 'q' to quit.")
+        raise RuntimeError('Webcam could not be opened.')
+
+    print("Press 'q' to quit")
 
     while True:
         ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
         if not ret:
             break
 
         faces = detector.detect(frame)
 
-        # Loop through each detected face
         for face in faces:
-            # Extract bbox and landmarks from the dictionary
-            bbox = face["bbox"]
-            landmarks = np.array(face["landmarks"])
-
+            bbox = face['bbox']
+            landmarks = face['landmarks']
             x1, y1, x2, y2 = map(int, bbox)
 
-            # Get the normalized embedding for the current face
             embedding = recognizer.get_normalized_embedding(frame, landmarks)
+            sim = compute_similarity(ref_embedding, embedding)  # compare with reference
 
-            # Compare with the reference embedding
-            sim = compute_similarity(ref_embedding, embedding)
-
-            # Draw results
-            label = f"Match ({sim:.2f})" if sim > threshold else f"Unknown ({sim:.2f})"
+            # green = match, red = unknown
+            label = f'Match ({sim:.2f})' if sim > threshold else f'Unknown ({sim:.2f})'
             color = (0, 255, 0) if sim > threshold else (0, 0, 255)
+
             cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
             cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
 
-        cv2.imshow("Face Recognition", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
+        cv2.imshow('Face Recognition', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 
     cap.release()
@@ -70,35 +72,26 @@ def run_video(detector, recognizer, ref_embedding: np.ndarray, threshold: float
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Face recognition using a reference image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the reference face image.")
+    parser = argparse.ArgumentParser(description='Face search using a reference image')
+    parser.add_argument('--image', type=str, required=True, help='Reference face image')
+    parser.add_argument('--threshold', type=float, default=0.4, help='Match threshold')
+    parser.add_argument('--detector', type=str, default='scrfd', choices=['retinaface', 'scrfd'])
     parser.add_argument(
-        "--detector", type=str, default="scrfd", choices=["retinaface", "scrfd"], help="Face detection method."
-    )
-    parser.add_argument(
-        "--recognizer",
+        '--recognizer',
         type=str,
-        default="arcface",
-        choices=["arcface", "mobileface", "sphereface"],
-        help="Face recognition method.",
+        default='arcface',
+        choices=['arcface', 'mobileface', 'sphereface'],
     )
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
     args = parser.parse_args()
 
-    if args.verbose:
-        from uniface import enable_logging
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    recognizer = get_recognizer(args.recognizer)
 
-        enable_logging()
-
-    print("Initializing models...")
-    detector = create_detector(method=args.detector)
-    recognizer = create_recognizer(method=args.recognizer)
-
-    print("Extracting reference embedding...")
+    print(f'Loading reference: {args.image}')
     ref_embedding = extract_reference_embedding(detector, recognizer, args.image)
 
-    run_video(detector, recognizer, ref_embedding)
+    run_webcam(detector, recognizer, ref_embedding, args.threshold)
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     main()

scripts/run_landmarks.py

@@ -0,0 +1,117 @@
+# 106-point facial landmark detection
+# Usage: python run_landmarks.py --image path/to/image.jpg
+#        python run_landmarks.py --webcam
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, Landmark106, RetinaFace
+
+
+def process_image(detector, landmarker, image_path: str, save_dir: str = 'outputs'):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    for i, face in enumerate(faces):
+        bbox = face['bbox']
+        x1, y1, x2, y2 = map(int, bbox)
+        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        landmarks = landmarker.get_landmarks(image, bbox)
+        print(f'  Face {i + 1}: {len(landmarks)} landmarks')
+
+        for x, y in landmarks.astype(int):
+            cv2.circle(image, (x, y), 1, (0, 255, 0), -1)
+
+        cv2.putText(
+            image,
+            f'Face {i + 1}',
+            (x1, y1 - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (0, 255, 0),
+            2,
+        )
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_landmarks.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def run_webcam(detector, landmarker):
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
+    if not cap.isOpened():
+        print('Cannot open webcam')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        for face in faces:
+            bbox = face['bbox']
+            x1, y1, x2, y2 = map(int, bbox)
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+            landmarks = landmarker.get_landmarks(frame, bbox)  # 106 points
+            for x, y in landmarks.astype(int):
+                cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
+
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow('106-Point Landmarks', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run facial landmark detection')
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--webcam', action='store_true', help='Use webcam')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--save_dir', type=str, default='outputs')
+    args = parser.parse_args()
+
+    if not args.image and not args.webcam:
+        parser.error('Either --image or --webcam must be specified')
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    landmarker = Landmark106()
+
+    if args.webcam:
+        run_webcam(detector, landmarker)
+    else:
+        process_image(detector, landmarker, args.image, args.save_dir)
+
+
+if __name__ == '__main__':
+    main()

scripts/run_recognition.py

@@ -1,81 +1,103 @@
-import cv2
+# Face recognition: extract embeddings or compare two faces
+# Usage: python run_recognition.py --image path/to/image.jpg
+#        python run_recognition.py --image1 face1.jpg --image2 face2.jpg
+
 import argparse
+
+import cv2
 import numpy as np
 
-# Use the new high-level factory functions for consistency
-from uniface.detection import create_detector
-from uniface.recognition import create_recognizer
+from uniface.detection import SCRFD, RetinaFace
+from uniface.face_utils import compute_similarity
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+def get_recognizer(name: str):
+    if name == 'arcface':
+        return ArcFace()
+    elif name == 'mobileface':
+        return MobileFace()
+    else:
+        return SphereFace()
 
 
 def run_inference(detector, recognizer, image_path: str):
-    """
-    Detect faces and extract embeddings from a single image.
-
-    Args:
-        detector: Initialized face detector.
-        recognizer: Initialized face recognition model.
-        image_path (str): Path to the input image.
-    """
     image = cv2.imread(image_path)
     if image is None:
         print(f"Error: Failed to load image from '{image_path}'")
         return
 
     faces = detector.detect(image)
-
     if not faces:
-        print("No faces detected.")
+        print('No faces detected.')
         return
 
-    print(f"Detected {len(faces)} face(s). Extracting embeddings for the first face...")
+    print(f'Detected {len(faces)} face(s). Extracting embedding for the first face...')
 
-    # Process the first detected face
-    first_face = faces[0]
-    landmarks = np.array(first_face['landmarks'])  # Convert landmarks to numpy array
-
-    # Extract embedding using the landmarks from the face dictionary
+    landmarks = faces[0]['landmarks']  # 5-point landmarks for alignment (already np.ndarray)
     embedding = recognizer.get_embedding(image, landmarks)
-    norm_embedding = recognizer.get_normalized_embedding(image, landmarks)
+    norm_embedding = recognizer.get_normalized_embedding(image, landmarks)  # L2 normalized
 
-    # Print some info about the embeddings
-    print(f"  - Embedding shape: {embedding.shape}")
-    print(f"  - L2 norm of unnormalized embedding: {np.linalg.norm(embedding):.4f}")
-    print(f"  - L2 norm of normalized embedding: {np.linalg.norm(norm_embedding):.4f}")
+    print(f'  Embedding shape: {embedding.shape}')
+    print(f'  L2 norm (raw): {np.linalg.norm(embedding):.4f}')
+    print(f'  L2 norm (normalized): {np.linalg.norm(norm_embedding):.4f}')
+
+
+def compare_faces(detector, recognizer, image1_path: str, image2_path: str, threshold: float = 0.35):
+    img1 = cv2.imread(image1_path)
+    img2 = cv2.imread(image2_path)
+
+    if img1 is None or img2 is None:
+        print('Error: Failed to load one or both images')
+        return
+
+    faces1 = detector.detect(img1)
+    faces2 = detector.detect(img2)
+
+    if not faces1 or not faces2:
+        print('Error: No faces detected in one or both images')
+        return
+
+    landmarks1 = faces1[0]['landmarks']
+    landmarks2 = faces2[0]['landmarks']
+
+    embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
+    embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)
+
+    # cosine similarity for normalized embeddings
+    similarity = compute_similarity(embedding1, embedding2, normalized=True)
+    is_match = similarity > threshold
+
+    print(f'Similarity: {similarity:.4f}')
+    print(f'Result: {"Same person" if is_match else "Different person"} (threshold: {threshold})')
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Extract face embeddings from a single image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the input image.")
+    parser = argparse.ArgumentParser(description='Face recognition and comparison')
+    parser.add_argument('--image', type=str, help='Single image for embedding extraction')
+    parser.add_argument('--image1', type=str, help='First image for comparison')
+    parser.add_argument('--image2', type=str, help='Second image for comparison')
+    parser.add_argument('--threshold', type=float, default=0.35, help='Similarity threshold')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
     parser.add_argument(
-        "--detector",
+        '--recognizer',
         type=str,
-        default="retinaface",
-        choices=['retinaface', 'scrfd'],
-        help="Face detection method to use."
-    )
-    parser.add_argument(
-        "--recognizer",
-        type=str,
-        default="arcface",
+        default='arcface',
         choices=['arcface', 'mobileface', 'sphereface'],
-        help="Face recognition method to use."
     )
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
     args = parser.parse_args()
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    recognizer = get_recognizer(args.recognizer)
 
-    print(f"Initializing detector: {args.detector}")
-    detector = create_detector(method=args.detector)
-
-    print(f"Initializing recognizer: {args.recognizer}")
-    recognizer = create_recognizer(method=args.recognizer)
-
-    run_inference(detector, recognizer, args.image)
+    if args.image1 and args.image2:
+        compare_faces(detector, recognizer, args.image1, args.image2, args.threshold)
+    elif args.image:
+        run_inference(detector, recognizer, args.image)
+    else:
+        print('Error: Provide --image or both --image1 and --image2')
+        parser.print_help()
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     main()

scripts/run_video_detection.py

@@ -0,0 +1,109 @@
+# Face detection on video files
+# Usage: python run_video_detection.py --input video.mp4 --output output.mp4
+
+import argparse
+from pathlib import Path
+
+import cv2
+from tqdm import tqdm
+
+from uniface import SCRFD, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def process_video(
+    detector,
+    input_path: str,
+    output_path: str,
+    threshold: float = 0.6,
+    show_preview: bool = False,
+):
+    cap = cv2.VideoCapture(input_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{input_path}'")
+        return
+
+    # get video properties
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+    print(f'Input: {input_path} ({width}x{height}, {fps:.1f} fps, {total_frames} frames)')
+    print(f'Output: {output_path}')
+
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # codec for .mp4
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    if not out.isOpened():
+        print(f"Error: Cannot create output video '{output_path}'")
+        cap.release()
+        return
+
+    frame_count = 0
+    total_faces = 0
+
+    for _ in tqdm(range(total_frames), desc='Processing', unit='frames'):
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+        total_faces += len(faces)
+
+        bboxes = [f['bbox'] for f in faces]
+        scores = [f['confidence'] for f in faces]
+        landmarks = [f['landmarks'] for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        out.write(frame)
+
+        if show_preview:
+            cv2.imshow("Processing - Press 'q' to cancel", frame)
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                print('\nCancelled by user')
+                break
+
+    cap.release()
+    out.release()
+    if show_preview:
+        cv2.destroyAllWindows()
+
+    avg_faces = total_faces / frame_count if frame_count > 0 else 0
+    print(f'\nDone! {frame_count} frames, {total_faces} faces ({avg_faces:.1f} avg/frame)')
+    print(f'Saved: {output_path}')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Process video with face detection')
+    parser.add_argument('--input', type=str, required=True, help='Input video path')
+    parser.add_argument('--output', type=str, required=True, help='Output video path')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--preview', action='store_true', help='Show live preview')
+    args = parser.parse_args()
+
+    if not Path(args.input).exists():
+        print(f"Error: Input file '{args.input}' does not exist")
+        return
+
+    Path(args.output).parent.mkdir(parents=True, exist_ok=True)
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    process_video(detector, args.input, args.output, args.threshold, args.preview)
+
+
+if __name__ == '__main__':
+    main()

scripts/sha256_generate.py

@@ -5,31 +5,24 @@ from pathlib import Path
 
 def compute_sha256(file_path: Path, chunk_size: int = 8192) -> str:
     sha256_hash = hashlib.sha256()
-    with file_path.open("rb") as f:
-        for chunk in iter(lambda: f.read(chunk_size), b""):
+    with file_path.open('rb') as f:
+        for chunk in iter(lambda: f.read(chunk_size), b''):
             sha256_hash.update(chunk)
     return sha256_hash.hexdigest()
 
 
 def main():
-    parser = argparse.ArgumentParser(
-        description="Compute SHA256 hash of a model weight file."
-    )
-    parser.add_argument(
-        "file",
-        type=Path,
-        help="Path to the model weight file (.onnx, .pth, etc)."
-    )
-
+    parser = argparse.ArgumentParser(description='Compute SHA256 hash of a file')
+    parser.add_argument('file', type=Path, help='Path to file')
     args = parser.parse_args()
 
     if not args.file.exists() or not args.file.is_file():
-        print(f"File does not exist: {args.file}")
+        print(f'File does not exist: {args.file}')
         return
 
     sha256 = compute_sha256(args.file)
-    print(f"`SHA256 hash for '{args.file.name}':\n{sha256}")
+    print(f"SHA256 hash for '{args.file.name}':\n{sha256}")
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     main()

tests/test_age_gender.py

@@ -0,0 +1,117 @@
+import numpy as np
+import pytest
+
+from uniface.attribute import AgeGender
+
+
+@pytest.fixture
+def age_gender_model():
+    return AgeGender()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(age_gender_model):
+    assert age_gender_model is not None, 'AgeGender model initialization failed.'
+
+
+def test_prediction_output_format(age_gender_model, mock_image, mock_bbox):
+    gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert isinstance(gender_id, int), f'Gender ID should be int, got {type(gender_id)}'
+    assert isinstance(age, int), f'Age should be int, got {type(age)}'
+
+
+def test_gender_values(age_gender_model, mock_image, mock_bbox):
+    gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert gender_id in [0, 1], f'Gender ID should be 0 (Female) or 1 (Male), got {gender_id}'
+
+
+def test_age_range(age_gender_model, mock_image, mock_bbox):
+    gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+    assert 0 <= age <= 120, f'Age should be between 0 and 120, got {age}'
+
+
+def test_different_bbox_sizes(age_gender_model, mock_image):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        gender_id, age = age_gender_model.predict(mock_image, bbox)
+        assert gender_id in [0, 1], f'Failed for bbox {bbox}'
+        assert 0 <= age <= 120, f'Age out of range for bbox {bbox}'
+
+
+def test_different_image_sizes(age_gender_model, mock_bbox):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+        assert gender_id in [0, 1], f'Failed for image size {size}'
+        assert 0 <= age <= 120, f'Age out of range for image size {size}'
+
+
+def test_consistency(age_gender_model, mock_image, mock_bbox):
+    gender_id1, age1 = age_gender_model.predict(mock_image, mock_bbox)
+    gender_id2, age2 = age_gender_model.predict(mock_image, mock_bbox)
+
+    assert gender_id1 == gender_id2, 'Same input should produce same gender prediction'
+    assert age1 == age2, 'Same input should produce same age prediction'
+
+
+def test_bbox_list_format(age_gender_model, mock_image):
+    bbox_list = [100, 100, 300, 300]
+    gender_id, age = age_gender_model.predict(mock_image, bbox_list)
+    assert gender_id in [0, 1], 'Should work with bbox as list'
+    assert 0 <= age <= 120, 'Age should be in valid range'
+
+
+def test_bbox_array_format(age_gender_model, mock_image):
+    bbox_array = np.array([100, 100, 300, 300])
+    gender_id, age = age_gender_model.predict(mock_image, bbox_array)
+    assert gender_id in [0, 1], 'Should work with bbox as numpy array'
+    assert 0 <= age <= 120, 'Age should be in valid range'
+
+
+def test_multiple_predictions(age_gender_model, mock_image):
+    bboxes = [
+        [50, 50, 150, 150],
+        [200, 200, 350, 350],
+        [400, 400, 550, 550],
+    ]
+
+    results = []
+    for bbox in bboxes:
+        gender_id, age = age_gender_model.predict(mock_image, bbox)
+        results.append((gender_id, age))
+
+    assert len(results) == 3, 'Should have 3 predictions'
+    for gender_id, age in results:
+        assert gender_id in [0, 1]
+        assert 0 <= age <= 120
+
+
+def test_age_is_positive(age_gender_model, mock_image, mock_bbox):
+    for _ in range(5):
+        gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+        assert age >= 0, f'Age should be non-negative, got {age}'
+
+
+def test_output_format_for_visualization(age_gender_model, mock_image, mock_bbox):
+    gender_id, age = age_gender_model.predict(mock_image, mock_bbox)
+    gender_str = 'Female' if gender_id == 0 else 'Male'
+    text = f'{gender_str}, {age}y'
+    assert isinstance(text, str), 'Should be able to format as string'
+    assert 'Male' in text or 'Female' in text, 'Text should contain gender'
+    assert 'y' in text, "Text should contain 'y' for years"

tests/test_factory.py

@@ -0,0 +1,274 @@
+import numpy as np
+import pytest
+
+from uniface import (
+    create_detector,
+    create_landmarker,
+    create_recognizer,
+    detect_faces,
+    list_available_detectors,
+)
+from uniface.constants import RetinaFaceWeights, SCRFDWeights
+
+
+# create_detector tests
+def test_create_detector_retinaface():
+    """
+    Test creating a RetinaFace detector using factory function.
+    """
+    detector = create_detector('retinaface')
+    assert detector is not None, 'Failed to create RetinaFace detector'
+
+
+def test_create_detector_scrfd():
+    """
+    Test creating a SCRFD detector using factory function.
+    """
+    detector = create_detector('scrfd')
+    assert detector is not None, 'Failed to create SCRFD detector'
+
+
+def test_create_detector_with_config():
+    """
+    Test creating detector with custom configuration.
+    """
+    detector = create_detector(
+        'retinaface',
+        model_name=RetinaFaceWeights.MNET_V2,
+        conf_thresh=0.8,
+        nms_thresh=0.3,
+    )
+    assert detector is not None, 'Failed to create detector with custom config'
+
+
+def test_create_detector_invalid_method():
+    """
+    Test that invalid detector method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_detector('invalid_method')
+
+
+def test_create_detector_scrfd_with_model():
+    """
+    Test creating SCRFD detector with specific model.
+    """
+    detector = create_detector('scrfd', model_name=SCRFDWeights.SCRFD_10G_KPS, conf_thresh=0.5)
+    assert detector is not None, 'Failed to create SCRFD with specific model'
+
+
+# create_recognizer tests
+def test_create_recognizer_arcface():
+    """
+    Test creating an ArcFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('arcface')
+    assert recognizer is not None, 'Failed to create ArcFace recognizer'
+
+
+def test_create_recognizer_mobileface():
+    """
+    Test creating a MobileFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('mobileface')
+    assert recognizer is not None, 'Failed to create MobileFace recognizer'
+
+
+def test_create_recognizer_sphereface():
+    """
+    Test creating a SphereFace recognizer using factory function.
+    """
+    recognizer = create_recognizer('sphereface')
+    assert recognizer is not None, 'Failed to create SphereFace recognizer'
+
+
+def test_create_recognizer_invalid_method():
+    """
+    Test that invalid recognizer method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_recognizer('invalid_method')
+
+
+# create_landmarker tests
+def test_create_landmarker():
+    """
+    Test creating a Landmark106 detector using factory function.
+    """
+    landmarker = create_landmarker('2d106det')
+    assert landmarker is not None, 'Failed to create Landmark106 detector'
+
+
+def test_create_landmarker_default():
+    """
+    Test creating landmarker with default parameters.
+    """
+    landmarker = create_landmarker()
+    assert landmarker is not None, 'Failed to create default landmarker'
+
+
+def test_create_landmarker_invalid_method():
+    """
+    Test that invalid landmarker method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_landmarker('invalid_method')
+
+
+# detect_faces tests
+def test_detect_faces_retinaface():
+    """
+    Test high-level detect_faces function with RetinaFace.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='retinaface')
+
+    assert isinstance(faces, list), 'detect_faces should return a list'
+
+
+def test_detect_faces_scrfd():
+    """
+    Test high-level detect_faces function with SCRFD.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='scrfd')
+
+    assert isinstance(faces, list), 'detect_faces should return a list'
+
+
+def test_detect_faces_with_threshold():
+    """
+    Test detect_faces with custom confidence threshold.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image, method='retinaface', conf_thresh=0.8)
+
+    assert isinstance(faces, list), 'detect_faces should return a list'
+
+    # All detections should respect threshold
+    for face in faces:
+        assert face['confidence'] >= 0.8, 'All detections should meet confidence threshold'
+
+
+def test_detect_faces_default_method():
+    """
+    Test detect_faces with default method (should use retinaface).
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(mock_image)  # No method specified
+
+    assert isinstance(faces, list), 'detect_faces should return a list with default method'
+
+
+def test_detect_faces_empty_image():
+    """
+    Test detect_faces on a blank image.
+    """
+    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
+    faces = detect_faces(empty_image, method='retinaface')
+
+    assert isinstance(faces, list), 'Should return a list even for empty image'
+    assert len(faces) == 0, 'Should detect no faces in blank image'
+
+
+# list_available_detectors tests
+def test_list_available_detectors():
+    """
+    Test that list_available_detectors returns a dictionary.
+    """
+    detectors = list_available_detectors()
+
+    assert isinstance(detectors, dict), 'Should return a dictionary of detectors'
+    assert len(detectors) > 0, 'Should have at least one detector available'
+
+
+def test_list_available_detectors_contents():
+    """
+    Test that list includes known detectors.
+    """
+    detectors = list_available_detectors()
+
+    # Should include at least these detectors
+    assert 'retinaface' in detectors, "Should include 'retinaface'"
+    assert 'scrfd' in detectors, "Should include 'scrfd'"
+
+
+# Integration tests
+def test_detector_inference_from_factory():
+    """
+    Test that detector created from factory can perform inference.
+    """
+    detector = create_detector('retinaface')
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    faces = detector.detect(mock_image)
+    assert isinstance(faces, list), 'Detector should return list of faces'
+
+
+def test_recognizer_inference_from_factory():
+    """
+    Test that recognizer created from factory can perform inference.
+    """
+    recognizer = create_recognizer('arcface')
+    mock_image = np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
+
+    embedding = recognizer.get_embedding(mock_image)
+    assert embedding is not None, 'Recognizer should return embedding'
+    assert embedding.shape[1] == 512, 'Should return 512-dimensional embedding'
+
+
+def test_landmarker_inference_from_factory():
+    """
+    Test that landmarker created from factory can perform inference.
+    """
+    landmarker = create_landmarker('2d106det')
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    mock_bbox = [100, 100, 300, 300]
+
+    landmarks = landmarker.get_landmarks(mock_image, mock_bbox)
+    assert landmarks is not None, 'Landmarker should return landmarks'
+    assert landmarks.shape == (106, 2), 'Should return 106 landmarks'
+
+
+def test_multiple_detector_creation():
+    """
+    Test that multiple detectors can be created independently.
+    """
+    detector1 = create_detector('retinaface')
+    detector2 = create_detector('scrfd')
+
+    assert detector1 is not None
+    assert detector2 is not None
+    assert detector1 is not detector2, 'Should create separate instances'
+
+
+def test_detector_with_different_configs():
+    """
+    Test creating multiple detectors with different configurations.
+    """
+    detector_high_thresh = create_detector('retinaface', conf_thresh=0.9)
+    detector_low_thresh = create_detector('retinaface', conf_thresh=0.3)
+
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    faces_high = detector_high_thresh.detect(mock_image)
+    faces_low = detector_low_thresh.detect(mock_image)
+
+    # Both should work
+    assert isinstance(faces_high, list)
+    assert isinstance(faces_low, list)
+
+
+def test_factory_returns_correct_types():
+    """
+    Test that factory functions return instances of the correct types.
+    """
+    from uniface import ArcFace, Landmark106, RetinaFace
+
+    detector = create_detector('retinaface')
+    recognizer = create_recognizer('arcface')
+    landmarker = create_landmarker('2d106det')
+
+    assert isinstance(detector, RetinaFace), 'Should return RetinaFace instance'
+    assert isinstance(recognizer, ArcFace), 'Should return ArcFace instance'
+    assert isinstance(landmarker, Landmark106), 'Should return Landmark106 instance'

tests/test_landmark.py

@@ -0,0 +1,107 @@
+import numpy as np
+import pytest
+
+from uniface.landmark import Landmark106
+
+
+@pytest.fixture
+def landmark_model():
+    return Landmark106()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(landmark_model):
+    assert landmark_model is not None, 'Landmark106 model initialization failed.'
+
+
+def test_landmark_detection(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    assert landmarks.shape == (106, 2), f'Expected shape (106, 2), got {landmarks.shape}'
+
+
+def test_landmark_dtype(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    assert landmarks.dtype == np.float32, f'Expected float32, got {landmarks.dtype}'
+
+
+def test_landmark_coordinates_within_image(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    x_coords = landmarks[:, 0]
+    y_coords = landmarks[:, 1]
+
+    x1, y1, x2, y2 = mock_bbox
+    margin = 50
+
+    x_in_bounds = np.sum((x_coords >= x1 - margin) & (x_coords <= x2 + margin))
+    y_in_bounds = np.sum((y_coords >= y1 - margin) & (y_coords <= y2 + margin))
+
+    assert x_in_bounds >= 95, f'Only {x_in_bounds}/106 x-coordinates within bounds'
+    assert y_in_bounds >= 95, f'Only {y_in_bounds}/106 y-coordinates within bounds'
+
+
+def test_different_bbox_sizes(landmark_model, mock_image):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        landmarks = landmark_model.get_landmarks(mock_image, bbox)
+        assert landmarks.shape == (106, 2), f'Failed for bbox {bbox}'
+
+
+def test_landmark_array_format(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+    landmarks_int = landmarks.astype(int)
+
+    assert landmarks_int.shape == (106, 2), 'Integer conversion should preserve shape'
+    assert landmarks_int.dtype in [np.int32, np.int64], 'Should convert to integer type'
+
+
+def test_consistency(landmark_model, mock_image, mock_bbox):
+    landmarks1 = landmark_model.get_landmarks(mock_image, mock_bbox)
+    landmarks2 = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    assert np.allclose(landmarks1, landmarks2), 'Same input should produce same landmarks'
+
+
+def test_different_image_sizes(landmark_model, mock_bbox):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+        assert landmarks.shape == (106, 2), f'Failed for image size {size}'
+
+
+def test_bbox_list_format(landmark_model, mock_image):
+    bbox_list = [100, 100, 300, 300]
+    landmarks = landmark_model.get_landmarks(mock_image, bbox_list)
+    assert landmarks.shape == (106, 2), 'Should work with bbox as list'
+
+
+def test_bbox_array_format(landmark_model, mock_image):
+    bbox_array = np.array([100, 100, 300, 300])
+    landmarks = landmark_model.get_landmarks(mock_image, bbox_array)
+    assert landmarks.shape == (106, 2), 'Should work with bbox as numpy array'
+
+
+def test_landmark_distribution(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    x_variance = np.var(landmarks[:, 0])
+    y_variance = np.var(landmarks[:, 1])
+
+    assert x_variance > 0, 'Landmarks should have variation in x-coordinates'
+    assert y_variance > 0, 'Landmarks should have variation in y-coordinates'

tests/test_recognition.py

@@ -0,0 +1,215 @@
+import numpy as np
+import pytest
+
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+@pytest.fixture
+def arcface_model():
+    """
+    Fixture to initialize the ArcFace model for testing.
+    """
+    return ArcFace()
+
+
+@pytest.fixture
+def mobileface_model():
+    """
+    Fixture to initialize the MobileFace model for testing.
+    """
+    return MobileFace()
+
+
+@pytest.fixture
+def sphereface_model():
+    """
+    Fixture to initialize the SphereFace model for testing.
+    """
+    return SphereFace()
+
+
+@pytest.fixture
+def mock_aligned_face():
+    """
+    Create a mock 112x112 aligned face image.
+    """
+    return np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_landmarks():
+    """
+    Create mock 5-point facial landmarks.
+    """
+    return np.array(
+        [
+            [38.2946, 51.6963],
+            [73.5318, 51.5014],
+            [56.0252, 71.7366],
+            [41.5493, 92.3655],
+            [70.7299, 92.2041],
+        ],
+        dtype=np.float32,
+    )
+
+
+# ArcFace Tests
+def test_arcface_initialization(arcface_model):
+    """
+    Test that the ArcFace model initializes correctly.
+    """
+    assert arcface_model is not None, 'ArcFace model initialization failed.'
+
+
+def test_arcface_embedding_shape(arcface_model, mock_aligned_face):
+    """
+    Test that ArcFace produces embeddings with the correct shape.
+    """
+    embedding = arcface_model.get_embedding(mock_aligned_face)
+
+    # ArcFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
+
+
+def test_arcface_normalized_embedding(arcface_model, mock_landmarks):
+    """
+    Test that normalized embeddings have unit length.
+    """
+    # Create a larger mock image for alignment
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = arcface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    # Check that embedding is normalized (L2 norm ≈ 1.0)
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
+
+
+def test_arcface_embedding_dtype(arcface_model, mock_aligned_face):
+    """
+    Test that embeddings have the correct data type.
+    """
+    embedding = arcface_model.get_embedding(mock_aligned_face)
+    assert embedding.dtype == np.float32, f'Expected float32, got {embedding.dtype}'
+
+
+def test_arcface_consistency(arcface_model, mock_aligned_face):
+    """
+    Test that the same input produces the same embedding.
+    """
+    embedding1 = arcface_model.get_embedding(mock_aligned_face)
+    embedding2 = arcface_model.get_embedding(mock_aligned_face)
+
+    assert np.allclose(embedding1, embedding2), 'Same input should produce same embedding'
+
+
+# MobileFace Tests
+def test_mobileface_initialization(mobileface_model):
+    """
+    Test that the MobileFace model initializes correctly.
+    """
+    assert mobileface_model is not None, 'MobileFace model initialization failed.'
+
+
+def test_mobileface_embedding_shape(mobileface_model, mock_aligned_face):
+    """
+    Test that MobileFace produces embeddings with the correct shape.
+    """
+    embedding = mobileface_model.get_embedding(mock_aligned_face)
+
+    # MobileFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
+
+
+def test_mobileface_normalized_embedding(mobileface_model, mock_landmarks):
+    """
+    Test that MobileFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = mobileface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
+
+
+# SphereFace Tests
+def test_sphereface_initialization(sphereface_model):
+    """
+    Test that the SphereFace model initializes correctly.
+    """
+    assert sphereface_model is not None, 'SphereFace model initialization failed.'
+
+
+def test_sphereface_embedding_shape(sphereface_model, mock_aligned_face):
+    """
+    Test that SphereFace produces embeddings with the correct shape.
+    """
+    embedding = sphereface_model.get_embedding(mock_aligned_face)
+
+    # SphereFace typically produces 512-dimensional embeddings
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
+
+
+def test_sphereface_normalized_embedding(sphereface_model, mock_landmarks):
+    """
+    Test that SphereFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = sphereface_model.get_normalized_embedding(mock_image, mock_landmarks)
+
+    norm = np.linalg.norm(embedding)
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
+
+
+# Cross-model comparison tests
+def test_different_models_different_embeddings(arcface_model, mobileface_model, mock_aligned_face):
+    """
+    Test that different models produce different embeddings for the same input.
+    """
+    arcface_emb = arcface_model.get_embedding(mock_aligned_face)
+    mobileface_emb = mobileface_model.get_embedding(mock_aligned_face)
+
+    # Embeddings should be different (with high probability for random input)
+    # We check that they're not identical
+    assert not np.allclose(arcface_emb, mobileface_emb), 'Different models should produce different embeddings'
+
+
+def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
+    """
+    Test computing similarity between embeddings.
+    """
+    # Get two embeddings
+    emb1 = arcface_model.get_embedding(mock_aligned_face)
+
+    # Create a slightly different image
+    mock_aligned_face2 = mock_aligned_face.copy()
+    mock_aligned_face2[:10, :10] = 0  # Modify a small region
+    emb2 = arcface_model.get_embedding(mock_aligned_face2)
+
+    # Compute cosine similarity
+    from uniface import compute_similarity
+
+    similarity = compute_similarity(emb1, emb2)
+
+    # Similarity should be between -1 and 1
+    assert -1.0 <= similarity <= 1.0, f'Similarity should be in [-1, 1], got {similarity}'
+
+
+def test_same_face_high_similarity(arcface_model, mock_aligned_face):
+    """
+    Test that the same face produces high similarity.
+    """
+    emb1 = arcface_model.get_embedding(mock_aligned_face)
+    emb2 = arcface_model.get_embedding(mock_aligned_face)
+
+    from uniface import compute_similarity
+
+    similarity = compute_similarity(emb1, emb2)
+
+    # Same image should have similarity close to 1.0
+    assert similarity > 0.99, f'Same face should have similarity > 0.99, got {similarity}'

tests/test_retinaface.py

@@ -7,9 +7,6 @@ from uniface.detection import RetinaFace
 
 @pytest.fixture
 def retinaface_model():
-    """
-    Fixture to initialize the RetinaFace model for testing.
-    """
     return RetinaFace(
         model_name=RetinaFaceWeights.MNET_V2,
         conf_thresh=0.5,
@@ -20,67 +17,39 @@ def retinaface_model():
 
 
 def test_model_initialization(retinaface_model):
-    """
-    Test that the RetinaFace model initializes correctly.
-    """
-    assert retinaface_model is not None, "Model initialization failed."
+    assert retinaface_model is not None, 'Model initialization failed.'
 
 
 def test_inference_on_640x640_image(retinaface_model):
-    """
-    Test inference on a 640x640 BGR image.
-    """
-    # Generate a mock 640x640 BGR image
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-
-    # Run inference - returns list of dictionaries
     faces = retinaface_model.detect(mock_image)
 
-    # Check output type
-    assert isinstance(faces, list), "Detections should be a list."
+    assert isinstance(faces, list), 'Detections should be a list.'
 
-    # Check that each face has the expected structure
     for face in faces:
-        assert isinstance(face, dict), "Each detection should be a dictionary."
-        assert "bbox" in face, "Each detection should have a 'bbox' key."
-        assert "confidence" in face, "Each detection should have a 'confidence' key."
-        assert "landmarks" in face, "Each detection should have a 'landmarks' key."
+        assert isinstance(face, dict), 'Each detection should be a dictionary.'
+        assert 'bbox' in face, "Each detection should have a 'bbox' key."
+        assert 'confidence' in face, "Each detection should have a 'confidence' key."
+        assert 'landmarks' in face, "Each detection should have a 'landmarks' key."
 
-        # Check bbox format
-        bbox = face["bbox"]
-        assert len(bbox) == 4, "BBox should have 4 values (x1, y1, x2, y2)."
+        bbox = face['bbox']
+        assert len(bbox) == 4, 'BBox should have 4 values (x1, y1, x2, y2).'
 
-        # Check landmarks format
-        landmarks = face["landmarks"]
-        assert len(landmarks) == 5, "Should have 5 landmark points."
-        assert all(len(pt) == 2 for pt in landmarks), "Each landmark should be (x, y)."
+        landmarks = face['landmarks']
+        assert len(landmarks) == 5, 'Should have 5 landmark points.'
+        assert all(len(pt) == 2 for pt in landmarks), 'Each landmark should be (x, y).'
 
 
 def test_confidence_threshold(retinaface_model):
-    """
-    Test that detections respect the confidence threshold.
-    """
-    # Generate a mock 640x640 BGR image
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-
-    # Run inference
     faces = retinaface_model.detect(mock_image)
 
-    # Ensure all detections have confidence scores above the threshold
     for face in faces:
-        confidence = face["confidence"]
-        assert confidence >= 0.5, f"Detection has confidence {confidence} below threshold 0.5"
+        confidence = face['confidence']
+        assert confidence >= 0.5, f'Detection has confidence {confidence} below threshold 0.5'
 
 
 def test_no_faces_detected(retinaface_model):
-    """
-    Test inference on an image without detectable faces.
-    """
-    # Generate an empty (black) 640x640 image
     empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
-
-    # Run inference
     faces = retinaface_model.detect(empty_image)
-
-    # Ensure no detections are found
-    assert len(faces) == 0, "Should detect no faces in a blank image."
+    assert len(faces) == 0, 'Should detect no faces in a blank image.'

tests/test_scrfd.py

@@ -0,0 +1,71 @@
+import numpy as np
+import pytest
+
+from uniface.constants import SCRFDWeights
+from uniface.detection import SCRFD
+
+
+@pytest.fixture
+def scrfd_model():
+    return SCRFD(
+        model_name=SCRFDWeights.SCRFD_500M_KPS,
+        conf_thresh=0.5,
+        nms_thresh=0.4,
+    )
+
+
+def test_model_initialization(scrfd_model):
+    assert scrfd_model is not None, 'Model initialization failed.'
+
+
+def test_inference_on_640x640_image(scrfd_model):
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(mock_image)
+
+    assert isinstance(faces, list), 'Detections should be a list.'
+
+    for face in faces:
+        assert isinstance(face, dict), 'Each detection should be a dictionary.'
+        assert 'bbox' in face, "Each detection should have a 'bbox' key."
+        assert 'confidence' in face, "Each detection should have a 'confidence' key."
+        assert 'landmarks' in face, "Each detection should have a 'landmarks' key."
+
+        bbox = face['bbox']
+        assert len(bbox) == 4, 'BBox should have 4 values (x1, y1, x2, y2).'
+
+        landmarks = face['landmarks']
+        assert len(landmarks) == 5, 'Should have 5 landmark points.'
+        assert all(len(pt) == 2 for pt in landmarks), 'Each landmark should be (x, y).'
+
+
+def test_confidence_threshold(scrfd_model):
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(mock_image)
+
+    for face in faces:
+        confidence = face['confidence']
+        assert confidence >= 0.5, f'Detection has confidence {confidence} below threshold 0.5'
+
+
+def test_no_faces_detected(scrfd_model):
+    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
+    faces = scrfd_model.detect(empty_image)
+    assert len(faces) == 0, 'Should detect no faces in a blank image.'
+
+
+def test_different_input_sizes(scrfd_model):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        faces = scrfd_model.detect(mock_image)
+        assert isinstance(faces, list), f'Should return list for size {size}'
+
+
+def test_scrfd_10g_model():
+    model = SCRFD(model_name=SCRFDWeights.SCRFD_10G_KPS, conf_thresh=0.5)
+    assert model is not None, 'SCRFD 10G model initialization failed.'
+
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = model.detect(mock_image)
+    assert isinstance(faces, list), 'SCRFD 10G should return list of detections.'

tests/test_utils.py

@@ -0,0 +1,262 @@
+import numpy as np
+import pytest
+
+from uniface import compute_similarity, face_alignment
+
+
+@pytest.fixture
+def mock_image():
+    """
+    Create a mock 640x640 BGR image.
+    """
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_landmarks():
+    """
+    Create mock 5-point facial landmarks.
+    Standard positions for a face roughly centered at (112/2, 112/2).
+    """
+    return np.array(
+        [
+            [38.2946, 51.6963],  # Left eye
+            [73.5318, 51.5014],  # Right eye
+            [56.0252, 71.7366],  # Nose
+            [41.5493, 92.3655],  # Left mouth corner
+            [70.7299, 92.2041],  # Right mouth corner
+        ],
+        dtype=np.float32,
+    )
+
+
+# compute_similarity tests
+def test_compute_similarity_same_embedding():
+    """
+    Test that similarity of an embedding with itself is 1.0.
+    """
+    embedding = np.random.randn(1, 512).astype(np.float32)
+    embedding = embedding / np.linalg.norm(embedding)  # Normalize
+
+    similarity = compute_similarity(embedding, embedding)
+    assert np.isclose(similarity, 1.0, atol=1e-5), f'Self-similarity should be 1.0, got {similarity}'
+
+
+def test_compute_similarity_range():
+    """
+    Test that similarity is always in the range [-1, 1].
+    """
+    # Test with multiple random embeddings
+    for _ in range(10):
+        emb1 = np.random.randn(1, 512).astype(np.float32)
+        emb2 = np.random.randn(1, 512).astype(np.float32)
+
+        # Normalize
+        emb1 = emb1 / np.linalg.norm(emb1)
+        emb2 = emb2 / np.linalg.norm(emb2)
+
+        similarity = compute_similarity(emb1, emb2)
+        assert -1.0 <= similarity <= 1.0, f'Similarity should be in [-1, 1], got {similarity}'
+
+
+def test_compute_similarity_orthogonal():
+    """
+    Test that orthogonal embeddings have similarity close to 0.
+    """
+    # Create orthogonal embeddings
+    emb1 = np.zeros((1, 512), dtype=np.float32)
+    emb1[0, 0] = 1.0  # [1, 0, 0, ..., 0]
+
+    emb2 = np.zeros((1, 512), dtype=np.float32)
+    emb2[0, 1] = 1.0  # [0, 1, 0, ..., 0]
+
+    similarity = compute_similarity(emb1, emb2)
+    assert np.isclose(similarity, 0.0, atol=1e-5), f'Orthogonal embeddings should have similarity 0.0, got {similarity}'
+
+
+def test_compute_similarity_opposite():
+    """
+    Test that opposite embeddings have similarity close to -1.
+    """
+    emb1 = np.ones((1, 512), dtype=np.float32)
+    emb1 = emb1 / np.linalg.norm(emb1)
+
+    emb2 = -emb1  # Opposite direction
+
+    similarity = compute_similarity(emb1, emb2)
+    assert np.isclose(similarity, -1.0, atol=1e-5), f'Opposite embeddings should have similarity -1.0, got {similarity}'
+
+
+def test_compute_similarity_symmetry():
+    """
+    Test that similarity(A, B) == similarity(B, A).
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    sim_12 = compute_similarity(emb1, emb2)
+    sim_21 = compute_similarity(emb2, emb1)
+
+    assert np.isclose(sim_12, sim_21), 'Similarity should be symmetric'
+
+
+def test_compute_similarity_dtype():
+    """
+    Test that compute_similarity returns a float.
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    similarity = compute_similarity(emb1, emb2)
+    assert isinstance(similarity, (float, np.floating)), f'Similarity should be float, got {type(similarity)}'
+
+
+# face_alignment tests
+def test_face_alignment_output_shape(mock_image, mock_landmarks):
+    """
+    Test that face_alignment produces output with the correct shape.
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert aligned.shape == (112, 112, 3), f'Expected shape (112, 112, 3), got {aligned.shape}'
+
+
+def test_face_alignment_dtype(mock_image, mock_landmarks):
+    """
+    Test that aligned face has the correct data type.
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert aligned.dtype == np.uint8, f'Expected uint8, got {aligned.dtype}'
+
+
+def test_face_alignment_different_sizes(mock_image, mock_landmarks):
+    """
+    Test face alignment with different output sizes.
+    """
+    # Only test sizes that are multiples of 112 or 128 as required by the function
+    test_sizes = [(112, 112), (128, 128), (224, 224)]
+
+    for size in test_sizes:
+        aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=size)
+        assert aligned.shape == (*size, 3), f'Failed for size {size}'
+
+
+def test_face_alignment_consistency(mock_image, mock_landmarks):
+    """
+    Test that the same input produces the same aligned face.
+    """
+    aligned1, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+    aligned2, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert np.allclose(aligned1, aligned2), 'Same input should produce same aligned face'
+
+
+def test_face_alignment_landmarks_as_list(mock_image):
+    """
+    Test that landmarks can be passed as a list of lists (converted to array).
+    """
+    landmarks_list = [
+        [38.2946, 51.6963],
+        [73.5318, 51.5014],
+        [56.0252, 71.7366],
+        [41.5493, 92.3655],
+        [70.7299, 92.2041],
+    ]
+
+    # Convert list to numpy array before passing to face_alignment
+    landmarks_array = np.array(landmarks_list, dtype=np.float32)
+    aligned, _ = face_alignment(mock_image, landmarks_array, image_size=(112, 112))
+    assert aligned.shape == (112, 112, 3), 'Should work with landmarks as array'
+
+
+def test_face_alignment_value_range(mock_image, mock_landmarks):
+    """
+    Test that aligned face pixel values are in valid range [0, 255].
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert np.all(aligned >= 0), 'Pixel values should be >= 0'
+    assert np.all(aligned <= 255), 'Pixel values should be <= 255'
+
+
+def test_face_alignment_not_all_zeros(mock_image, mock_landmarks):
+    """
+    Test that aligned face is not all zeros (actual transformation occurred).
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    # At least some pixels should be non-zero
+    assert np.any(aligned > 0), 'Aligned face should have some non-zero pixels'
+
+
+def test_face_alignment_from_different_positions(mock_image):
+    """
+    Test alignment with landmarks at different positions in the image.
+    """
+    # Landmarks at different positions
+    positions = [
+        np.array(
+            [[100, 100], [150, 100], [125, 130], [110, 150], [140, 150]],
+            dtype=np.float32,
+        ),
+        np.array(
+            [[300, 200], [350, 200], [325, 230], [310, 250], [340, 250]],
+            dtype=np.float32,
+        ),
+        np.array(
+            [[500, 400], [550, 400], [525, 430], [510, 450], [540, 450]],
+            dtype=np.float32,
+        ),
+    ]
+
+    for landmarks in positions:
+        aligned, _ = face_alignment(mock_image, landmarks, image_size=(112, 112))
+        assert aligned.shape == (112, 112, 3), f'Failed for landmarks at {landmarks[0]}'
+
+
+def test_face_alignment_landmark_count(mock_image):
+    """
+    Test that face_alignment works specifically with 5-point landmarks.
+    """
+    # Standard 5-point landmarks
+    landmarks_5pt = np.array(
+        [
+            [38.2946, 51.6963],
+            [73.5318, 51.5014],
+            [56.0252, 71.7366],
+            [41.5493, 92.3655],
+            [70.7299, 92.2041],
+        ],
+        dtype=np.float32,
+    )
+
+    aligned, _ = face_alignment(mock_image, landmarks_5pt, image_size=(112, 112))
+    assert aligned.shape == (112, 112, 3), 'Should work with 5-point landmarks'
+
+
+def test_compute_similarity_with_recognition_embeddings():
+    """
+    Test compute_similarity with realistic embedding dimensions.
+    """
+    # Simulate ArcFace/MobileFace/SphereFace embeddings (512-dim)
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize (as done in get_normalized_embedding)
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    similarity = compute_similarity(emb1, emb2)
+
+    # Should be a valid similarity score
+    assert -1.0 <= similarity <= 1.0
+    assert isinstance(similarity, (float, np.floating))

uniface/__init__.py

@@ -11,9 +11,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__license__ = "MIT"
-__author__ = "Yakhyokhuja Valikhujaev"
-__version__ = "0.1.9"
+__license__ = 'MIT'
+__author__ = 'Yakhyokhuja Valikhujaev'
+__version__ = '1.3.2'
 
 
 from uniface.face_utils import compute_similarity, face_alignment
@@ -21,42 +21,56 @@ from uniface.log import Logger, enable_logging
 from uniface.model_store import verify_model_weights
 from uniface.visualization import draw_detections
 
+from .analyzer import FaceAnalyzer
 from .attribute import AgeGender
+from .face import Face
+
 try:
     from .attribute import Emotion
 except ImportError:
     Emotion = None  # PyTorch not installed
-from .detection import SCRFD, RetinaFace, create_detector, detect_faces, list_available_detectors
+from .detection import (
+    SCRFD,
+    RetinaFace,
+    YOLOv5Face,
+    create_detector,
+    detect_faces,
+    list_available_detectors,
+)
 from .landmark import Landmark106, create_landmarker
 from .recognition import ArcFace, MobileFace, SphereFace, create_recognizer
 
 __all__ = [
-    "__author__",
-    "__license__",
-    "__version__",
+    '__author__',
+    '__license__',
+    '__version__',
+    # Core classes
+    'Face',
+    'FaceAnalyzer',
     # Factory functions
-    "create_detector",
-    "create_landmarker",
-    "create_recognizer",
-    "detect_faces",
-    "list_available_detectors",
+    'create_detector',
+    'create_landmarker',
+    'create_recognizer',
+    'detect_faces',
+    'list_available_detectors',
     # Detection models
-    "RetinaFace",
-    "SCRFD",
+    'RetinaFace',
+    'SCRFD',
+    'YOLOv5Face',
     # Recognition models
-    "ArcFace",
-    "MobileFace",
-    "SphereFace",
+    'ArcFace',
+    'MobileFace',
+    'SphereFace',
     # Landmark models
-    "Landmark106",
+    'Landmark106',
     # Attribute models
-    "AgeGender",
-    "Emotion",
+    'AgeGender',
+    'Emotion',
     # Utilities
-    "compute_similarity",
-    "draw_detections",
-    "face_alignment",
-    "verify_model_weights",
-    "Logger",
-    "enable_logging",
+    'compute_similarity',
+    'draw_detections',
+    'face_alignment',
+    'verify_model_weights',
+    'Logger',
+    'enable_logging',
 ]

uniface/analyzer.py

@@ -0,0 +1,83 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import List, Optional
+
+import numpy as np
+
+from uniface.attribute.age_gender import AgeGender
+from uniface.detection.base import BaseDetector
+from uniface.face import Face
+from uniface.log import Logger
+from uniface.recognition.base import BaseRecognizer
+
+__all__ = ['FaceAnalyzer']
+
+
+class FaceAnalyzer:
+    """Unified face analyzer combining detection, recognition, and attributes."""
+
+    def __init__(
+        self,
+        detector: BaseDetector,
+        recognizer: Optional[BaseRecognizer] = None,
+        age_gender: Optional[AgeGender] = None,
+    ) -> None:
+        self.detector = detector
+        self.recognizer = recognizer
+        self.age_gender = age_gender
+
+        Logger.info(f'Initialized FaceAnalyzer with detector={detector.__class__.__name__}')
+        if recognizer:
+            Logger.info(f'  - Recognition enabled: {recognizer.__class__.__name__}')
+        if age_gender:
+            Logger.info(f'  - Age/Gender enabled: {age_gender.__class__.__name__}')
+
+    def analyze(self, image: np.ndarray) -> List[Face]:
+        """Analyze faces in an image."""
+        detections = self.detector.detect(image)
+        Logger.debug(f'Detected {len(detections)} face(s)')
+
+        faces = []
+        for idx, detection in enumerate(detections):
+            bbox = detection['bbox']
+            confidence = detection['confidence']
+            landmarks = detection['landmarks']
+
+            embedding = None
+            if self.recognizer is not None:
+                try:
+                    embedding = self.recognizer.get_normalized_embedding(image, landmarks)
+                    Logger.debug(f'  Face {idx + 1}: Extracted embedding with shape {embedding.shape}')
+                except Exception as e:
+                    Logger.warning(f'  Face {idx + 1}: Failed to extract embedding: {e}')
+
+            age, gender = None, None
+            if self.age_gender is not None:
+                try:
+                    gender, age = self.age_gender.predict(image, bbox)
+                    Logger.debug(f'  Face {idx + 1}: Age={age}, Gender={gender}')
+                except Exception as e:
+                    Logger.warning(f'  Face {idx + 1}: Failed to predict age/gender: {e}')
+
+            face = Face(
+                bbox=bbox,
+                confidence=confidence,
+                landmarks=landmarks,
+                embedding=embedding,
+                age=age,
+                gender=gender,
+            )
+            faces.append(face)
+
+        Logger.info(f'Analysis complete: {len(faces)} face(s) processed')
+        return faces
+
+    def __repr__(self) -> str:
+        parts = [f'FaceAnalyzer(detector={self.detector.__class__.__name__}']
+        if self.recognizer:
+            parts.append(f'recognizer={self.recognizer.__class__.__name__}')
+        if self.age_gender:
+            parts.append(f'age_gender={self.age_gender.__class__.__name__}')
+        return ', '.join(parts) + ')'

uniface/attribute/__init__.py

@@ -2,7 +2,8 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Dict, Any, List, Union
+from typing import Any, Dict, List, Union
+
 import numpy as np
 
 from uniface.attribute.age_gender import AgeGender
@@ -12,18 +13,14 @@ from uniface.constants import AgeGenderWeights, DDAMFNWeights
 # Emotion requires PyTorch - make it optional
 try:
     from uniface.attribute.emotion import Emotion
+
     _EMOTION_AVAILABLE = True
 except ImportError:
     Emotion = None
     _EMOTION_AVAILABLE = False
 
 # Public API for the attribute module
-__all__ = [
-    "AgeGender",
-    "Emotion",
-    "create_attribute_predictor",
-    "predict_attributes"
-]
+__all__ = ['AgeGender', 'Emotion', 'create_attribute_predictor', 'predict_attributes']
 
 # A mapping from model enums to their corresponding attribute classes
 _ATTRIBUTE_MODELS = {
@@ -35,10 +32,7 @@ if _EMOTION_AVAILABLE:
     _ATTRIBUTE_MODELS.update({model: Emotion for model in DDAMFNWeights})
 
 
-def create_attribute_predictor(
-    model_name: Union[AgeGenderWeights, DDAMFNWeights],
-    **kwargs: Any
-) -> Attribute:
+def create_attribute_predictor(model_name: Union[AgeGenderWeights, DDAMFNWeights], **kwargs: Any) -> Attribute:
     """
     Factory function to create an attribute predictor instance.
 
@@ -59,17 +53,16 @@ def create_attribute_predictor(
     model_class = _ATTRIBUTE_MODELS.get(model_name)
 
     if model_class is None:
-        raise ValueError(f"Unsupported attribute model: {model_name}. "
-                         f"Please choose from AgeGenderWeights or DDAMFNWeights.")
+        raise ValueError(
+            f'Unsupported attribute model: {model_name}. Please choose from AgeGenderWeights or DDAMFNWeights.'
+        )
 
     # Pass model_name to the constructor, as some classes might need it
     return model_class(model_name=model_name, **kwargs)
 
 
 def predict_attributes(
-    image: np.ndarray,
-    detections: List[Dict[str, np.ndarray]],
-    predictor: Attribute
+    image: np.ndarray, detections: List[Dict[str, np.ndarray]], predictor: Attribute
 ) -> List[Dict[str, Any]]:
     """
     High-level API to predict attributes for multiple detected faces.
@@ -95,8 +88,8 @@ def predict_attributes(
             face['attributes'] = {}
 
         if isinstance(predictor, AgeGender):
-            gender, age = predictor(image, face['bbox'])
-            face['attributes']['gender'] = gender
+            gender_id, age = predictor(image, face['bbox'])
+            face['attributes']['gender_id'] = gender_id
             face['attributes']['age'] = age
         elif isinstance(predictor, Emotion):
             emotion, confidence = predictor(image, face['landmark'])

uniface/attribute/age_gender.py

@@ -2,7 +2,7 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import List, Tuple, Union
+from typing import List, Optional, Tuple, Union
 
 import cv2
 import numpy as np
@@ -14,7 +14,7 @@ from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
 
-__all__ = ["AgeGender"]
+__all__ = ['AgeGender']
 
 
 class AgeGender(Attribute):
@@ -22,20 +22,32 @@ class AgeGender(Attribute):
     Age and gender prediction model using ONNX Runtime.
 
     This class inherits from the base `Attribute` class and implements the
-    functionality for predicting age (in years) and gender (0 for female,
-    1 for male) from a face image. It requires a bounding box to locate the face.
+    functionality for predicting age (in years) and gender ID (0 for Female,
+    1 for Male) from a face image. It requires a bounding box to locate the face.
+
+    Args:
+        model_name (AgeGenderWeights): The enum specifying the model weights to load.
+            Defaults to `AgeGenderWeights.DEFAULT`.
+        input_size (Optional[Tuple[int, int]]): Input size (height, width).
+            If None, automatically detected from model metadata. Defaults to None.
     """
 
-    def __init__(self, model_name: AgeGenderWeights = AgeGenderWeights.DEFAULT) -> None:
+    def __init__(
+        self,
+        model_name: AgeGenderWeights = AgeGenderWeights.DEFAULT,
+        input_size: Optional[Tuple[int, int]] = None,
+    ) -> None:
         """
         Initializes the AgeGender prediction model.
 
         Args:
-            model_name (AgeGenderWeights): The enum specifying the model weights
-                                           to load.
+            model_name (AgeGenderWeights): The enum specifying the model weights to load.
+            input_size (Optional[Tuple[int, int]]): Input size (height, width).
+                If None, automatically detected from model metadata. Defaults to None.
         """
-        Logger.info(f"Initializing AgeGender with model={model_name.name}")
+        Logger.info(f'Initializing AgeGender with model={model_name.name}')
         self.model_path = verify_model_weights(model_name)
+        self._user_input_size = input_size  # Store user preference
         self._initialize_model()
 
     def _initialize_model(self) -> None:
@@ -47,12 +59,27 @@ class AgeGender(Attribute):
             # Get model input details from the loaded model
             input_meta = self.session.get_inputs()[0]
             self.input_name = input_meta.name
-            self.input_size = tuple(input_meta.shape[2:4])  # (height, width)
+
+            # Use user-provided size if given, otherwise auto-detect from model
+            model_input_size = tuple(input_meta.shape[2:4])  # (height, width)
+            if self._user_input_size is not None:
+                self.input_size = self._user_input_size
+                if self._user_input_size != model_input_size:
+                    Logger.warning(
+                        f'Using custom input_size {self.input_size}, '
+                        f'but model expects {model_input_size}. This may affect accuracy.'
+                    )
+            else:
+                self.input_size = model_input_size
+
             self.output_names = [output.name for output in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized AgeGender model with input size {self.input_size}")
+            Logger.info(f'Successfully initialized AgeGender model with input size {self.input_size}')
         except Exception as e:
-            Logger.error(f"Failed to load AgeGender model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize AgeGender model: {e}")
+            Logger.error(
+                f"Failed to load AgeGender model from '{self.model_path}'",
+                exc_info=True,
+            )
+            raise RuntimeError(f'Failed to initialize AgeGender model: {e}') from e
 
     def preprocess(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> np.ndarray:
         """
@@ -76,11 +103,15 @@ class AgeGender(Attribute):
         aligned_face, _ = bbox_center_alignment(image, center, self.input_size[1], scale, rotation)
 
         blob = cv2.dnn.blobFromImage(
-            aligned_face, scalefactor=1.0, size=self.input_size[::-1], mean=(0.0, 0.0, 0.0), swapRB=True
+            aligned_face,
+            scalefactor=1.0,
+            size=self.input_size[::-1],
+            mean=(0.0, 0.0, 0.0),
+            swapRB=True,
         )
         return blob
 
-    def postprocess(self, prediction: np.ndarray) -> Tuple[str, int]:
+    def postprocess(self, prediction: np.ndarray) -> Tuple[int, int]:
         """
         Processes the raw model output to extract gender and age.
 
@@ -88,17 +119,16 @@ class AgeGender(Attribute):
             prediction (np.ndarray): The raw output from the model inference.
 
         Returns:
-            Tuple[str, int]: A tuple containing the predicted gender label ("Female" or "Male")
+            Tuple[int, int]: A tuple containing the predicted gender ID (0 for Female, 1 for Male)
                              and age (in years).
         """
         # First two values are gender logits
         gender_id = int(np.argmax(prediction[:2]))
-        gender = "Female" if gender_id == 0 else "Male"
         # Third value is normalized age, scaled by 100
         age = int(np.round(prediction[2] * 100))
-        return gender, age
+        return gender_id, age
 
-    def predict(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[str, int]:
+    def predict(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[int, int]:
         """
         Predicts age and gender for a single face specified by a bounding box.
 
@@ -107,22 +137,22 @@ class AgeGender(Attribute):
             bbox (Union[List, np.ndarray]): The face bounding box coordinates [x1, y1, x2, y2].
 
         Returns:
-            Tuple[str, int]: A tuple containing the predicted gender label and age.
+            Tuple[int, int]: A tuple containing the predicted gender ID (0 for Female, 1 for Male) and age.
         """
         face_blob = self.preprocess(image, bbox)
         prediction = self.session.run(self.output_names, {self.input_name: face_blob})[0][0]
-        gender, age = self.postprocess(prediction)
-        return gender, age
+        gender_id, age = self.postprocess(prediction)
+        return gender_id, age
 
 
 # TODO: below is only for testing, remove it later
-if __name__ == "__main__":
+if __name__ == '__main__':
     # To run this script, you need to have uniface.detection installed
     # or available in your path.
     from uniface.constants import RetinaFaceWeights
     from uniface.detection import create_detector
 
-    print("Initializing models for live inference...")
+    print('Initializing models for live inference...')
     # 1. Initialize the face detector
     # Using a smaller model for faster real-time performance
     detector = create_detector(model_name=RetinaFaceWeights.MNET_V2)
@@ -133,14 +163,14 @@ if __name__ == "__main__":
     # 3. Start webcam capture
     cap = cv2.VideoCapture(0)
     if not cap.isOpened():
-        print("Error: Could not open webcam.")
+        print('Error: Could not open webcam.')
         exit()
 
     print("Starting webcam feed. Press 'q' to quit.")
     while True:
         ret, frame = cap.read()
         if not ret:
-            print("Error: Failed to capture frame.")
+            print('Error: Failed to capture frame.')
             break
 
         # Detect faces in the current frame
@@ -148,25 +178,34 @@ if __name__ == "__main__":
 
         # For each detected face, predict age and gender
         for detection in detections:
-            box = detection["bbox"]
+            box = detection['bbox']
             x1, y1, x2, y2 = map(int, box)
 
             # Predict attributes
-            gender, age = age_gender_predictor.predict(frame, box)
+            gender_id, age = age_gender_predictor.predict(frame, box)
+            gender_str = 'Female' if gender_id == 0 else 'Male'
 
             # Prepare text and draw on the frame
-            label = f"{gender}, {age}"
+            label = f'{gender_str}, {age}'
             cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-            cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
+            cv2.putText(
+                frame,
+                label,
+                (x1, y1 - 10),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                0.8,
+                (0, 255, 0),
+                2,
+            )
 
         # Display the resulting frame
         cv2.imshow("Age and Gender Inference (Press 'q' to quit)", frame)
 
         # Break the loop if 'q' is pressed
-        if cv2.waitKey(1) & 0xFF == ord("q"):
+        if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 
     # Release resources
     cap.release()
     cv2.destroyAllWindows()
-    print("Inference stopped.")
+    print('Inference stopped.')

uniface/attribute/base.py

@@ -4,6 +4,7 @@
 
 from abc import ABC, abstractmethod
 from typing import Any
+
 import numpy as np
 
 
@@ -26,7 +27,7 @@ class Attribute(ABC):
         inference session (e.g., ONNX Runtime, PyTorch), and any necessary
         warm-up procedures to prepare the model for prediction.
         """
-        raise NotImplementedError("Subclasses must implement the _initialize_model method.")
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
 
     @abstractmethod
     def preprocess(self, image: np.ndarray, *args: Any) -> Any:
@@ -46,7 +47,7 @@ class Attribute(ABC):
         Returns:
             The preprocessed data ready for model inference.
         """
-        raise NotImplementedError("Subclasses must implement the preprocess method.")
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
 
     @abstractmethod
     def postprocess(self, prediction: Any) -> Any:
@@ -63,7 +64,7 @@ class Attribute(ABC):
         Returns:
             The final, processed attributes.
         """
-        raise NotImplementedError("Subclasses must implement the postprocess method.")
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
 
     @abstractmethod
     def predict(self, image: np.ndarray, *args: Any) -> Any:
@@ -82,7 +83,7 @@ class Attribute(ABC):
         Returns:
             The final predicted attributes.
         """
-        raise NotImplementedError("Subclasses must implement the predict method.")
+        raise NotImplementedError('Subclasses must implement the predict method.')
 
     def __call__(self, *args, **kwargs) -> Any:
         """

uniface/attribute/emotion.py

@@ -2,18 +2,19 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from typing import List, Tuple, Union
+
 import cv2
-import torch
 import numpy as np
-from typing import Tuple, Union, List
+import torch
 
 from uniface.attribute.base import Attribute
-from uniface.log import Logger
 from uniface.constants import DDAMFNWeights
 from uniface.face_utils import face_alignment
+from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 
-__all__ = ["Emotion"]
+__all__ = ['Emotion']
 
 
 class Emotion(Attribute):
@@ -37,15 +38,30 @@ class Emotion(Attribute):
             model_weights (DDAMFNWeights): The enum for the model weights to load.
             input_size (Tuple[int, int]): The expected input size for the model.
         """
-        Logger.info(f"Initializing Emotion with model={model_weights.name}")
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        Logger.info(f'Initializing Emotion with model={model_weights.name}')
+
+        if torch.backends.mps.is_available():
+            self.device = torch.device('mps')
+        elif torch.cuda.is_available():
+            self.device = torch.device('cuda')
+        else:
+            self.device = torch.device('cpu')
+
         self.input_size = input_size
         self.model_path = verify_model_weights(model_weights)
 
         # Define emotion labels based on the selected model
-        self.emotion_labels = ["Neutral", "Happy", "Sad", "Surprise", "Fear", "Disgust", "Angry"]
+        self.emotion_labels = [
+            'Neutral',
+            'Happy',
+            'Sad',
+            'Surprise',
+            'Fear',
+            'Disgust',
+            'Angry',
+        ]
         if model_weights == DDAMFNWeights.AFFECNET8:
-            self.emotion_labels.append("Contempt")
+            self.emotion_labels.append('Contempt')
 
         self._initialize_model()
 
@@ -60,10 +76,10 @@ class Emotion(Attribute):
             dummy_input = torch.randn(1, 3, *self.input_size).to(self.device)
             with torch.no_grad():
                 self.model(dummy_input)
-            Logger.info(f"Successfully initialized Emotion model on {self.device}")
+            Logger.info(f'Successfully initialized Emotion model on {self.device}')
         except Exception as e:
             Logger.error(f"Failed to load Emotion model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize Emotion model: {e}")
+            raise RuntimeError(f'Failed to initialize Emotion model: {e}') from e
 
     def preprocess(self, image: np.ndarray, landmark: Union[List, np.ndarray]) -> torch.Tensor:
         """
@@ -77,7 +93,7 @@ class Emotion(Attribute):
             torch.Tensor: The preprocessed image tensor ready for inference.
         """
         landmark = np.asarray(landmark)
-        
+
         aligned_image, _ = face_alignment(image, landmark)
 
         # Convert BGR to RGB, resize, normalize, and convert to a CHW tensor
@@ -114,11 +130,11 @@ class Emotion(Attribute):
 
 
 # TODO: below is only for testing, remove it later
-if __name__ == "__main__":
-    from uniface.detection import create_detector
+if __name__ == '__main__':
     from uniface.constants import RetinaFaceWeights
+    from uniface.detection import create_detector
 
-    print("Initializing models for live inference...")
+    print('Initializing models for live inference...')
     # 1. Initialize the face detector
     # Using a smaller model for faster real-time performance
     detector = create_detector(model_name=RetinaFaceWeights.MNET_V2)
@@ -129,14 +145,14 @@ if __name__ == "__main__":
     # 3. Start webcam capture
     cap = cv2.VideoCapture(0)
     if not cap.isOpened():
-        print("Error: Could not open webcam.")
+        print('Error: Could not open webcam.')
         exit()
 
     print("Starting webcam feed. Press 'q' to quit.")
     while True:
         ret, frame = cap.read()
         if not ret:
-            print("Error: Failed to capture frame.")
+            print('Error: Failed to capture frame.')
             break
 
         # Detect faces in the current frame.
@@ -151,11 +167,19 @@ if __name__ == "__main__":
 
             # Predict attributes using the landmark
             emotion, confidence = emotion_predictor.predict(frame, landmark)
-            
+
             # Prepare text and draw on the frame
-            label = f"{emotion} ({confidence:.2f})"
+            label = f'{emotion} ({confidence:.2f})'
             cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
-            cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 0, 0), 2)
+            cv2.putText(
+                frame,
+                label,
+                (x1, y1 - 10),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                0.8,
+                (255, 0, 0),
+                2,
+            )
 
         # Display the resulting frame
         cv2.imshow("Emotion Inference (Press 'q' to quit)", frame)
@@ -167,4 +191,4 @@ if __name__ == "__main__":
     # Release resources
     cap.release()
     cv2.destroyAllWindows()
-    print("Inference stopped.")
+    print('Inference stopped.')

uniface/common.py

@@ -2,12 +2,22 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import cv2
-import math
 import itertools
+import math
+from typing import List, Optional, Tuple
+
+import cv2
 import numpy as np
 
-from typing import Tuple, List
+__all__ = [
+    'resize_image',
+    'generate_anchors',
+    'non_max_suppression',
+    'decode_boxes',
+    'decode_landmarks',
+    'distance2bbox',
+    'distance2kps',
+]
 
 
 def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
@@ -45,26 +55,19 @@ def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.
 
 def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
     """
-    Generate anchor boxes for a given image size.
+    Generate anchor boxes for a given image size (RetinaFace specific).
 
     Args:
         image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640).
 
     Returns:
-        np.ndarray: Anchor box coordinates as a NumPy array.
+        np.ndarray: Anchor box coordinates as a NumPy array with shape (num_anchors, 4).
     """
-    image_size = image_size
-
     steps = [8, 16, 32]
     min_sizes = [[16, 32], [64, 128], [256, 512]]
 
     anchors = []
-    feature_maps = [
-        [
-            math.ceil(image_size[0] / step),
-            math.ceil(image_size[1] / step)
-        ] for step in steps
-    ]
+    feature_maps = [[math.ceil(image_size[0] / step), math.ceil(image_size[1] / step)] for step in steps]
 
     for k, (map_height, map_width) in enumerate(feature_maps):
         step = steps[k]
@@ -82,16 +85,16 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
     return output
 
 
-def non_max_supression(dets: List[np.ndarray], threshold: float):
+def non_max_suppression(dets: np.ndarray, threshold: float) -> List[int]:
     """
     Apply Non-Maximum Suppression (NMS) to reduce overlapping bounding boxes based on a threshold.
 
     Args:
-        dets (numpy.ndarray): Array of detections with each row as [x1, y1, x2, y2, score].
+        dets (np.ndarray): Array of detections with each row as [x1, y1, x2, y2, score].
         threshold (float): IoU threshold for suppression.
 
     Returns:
-        list: Indices of bounding boxes retained after suppression.
+        List[int]: Indices of bounding boxes retained after suppression.
     """
     x1 = dets[:, 0]
     y1 = dets[:, 1]
@@ -122,19 +125,21 @@ def non_max_supression(dets: List[np.ndarray], threshold: float):
     return keep
 
 
-def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
+def decode_boxes(loc: np.ndarray, priors: np.ndarray, variances: Optional[List[float]] = None) -> np.ndarray:
     """
     Decode locations from predictions using priors to undo
-    the encoding done for offset regression at train time.
+    the encoding done for offset regression at train time (RetinaFace specific).
 
     Args:
         loc (np.ndarray): Location predictions for loc layers, shape: [num_priors, 4]
         priors (np.ndarray): Prior boxes in center-offset form, shape: [num_priors, 4]
-        variances (list[float]): Variances of prior boxes
+        variances (Optional[List[float]]): Variances of prior boxes. Defaults to [0.1, 0.2].
 
     Returns:
-        np.ndarray: Decoded bounding box predictions
+        np.ndarray: Decoded bounding box predictions with shape [num_priors, 4]
     """
+    if variances is None:
+        variances = [0.1, 0.2]
     # Compute centers of predicted boxes
     cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:]
 
@@ -149,18 +154,22 @@ def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
     return boxes
 
 
-def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
+def decode_landmarks(
+    predictions: np.ndarray, priors: np.ndarray, variances: Optional[List[float]] = None
+) -> np.ndarray:
     """
-    Decode landmark predictions using prior boxes.
+    Decode landmark predictions using prior boxes (RetinaFace specific).
 
     Args:
         predictions (np.ndarray): Landmark predictions, shape: [num_priors, 10]
         priors (np.ndarray): Prior boxes, shape: [num_priors, 4]
-        variances (list): Scaling factors for landmark offsets.
+        variances (Optional[List[float]]): Scaling factors for landmark offsets. Defaults to [0.1, 0.2].
 
     Returns:
         np.ndarray: Decoded landmarks, shape: [num_priors, 10]
     """
+    if variances is None:
+        variances = [0.1, 0.2]
 
     # Reshape predictions to [num_priors, 5, 2] to process landmark points
     predictions = predictions.reshape(predictions.shape[0], 5, 2)
@@ -176,3 +185,59 @@ def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
     landmarks = landmarks.reshape(landmarks.shape[0], -1)
 
     return landmarks
+
+
+def distance2bbox(points: np.ndarray, distance: np.ndarray, max_shape: Optional[Tuple[int, int]] = None) -> np.ndarray:
+    """
+    Decode distance prediction to bounding box (SCRFD specific).
+
+    Args:
+        points (np.ndarray): Anchor points with shape (n, 2), [x, y].
+        distance (np.ndarray): Distance from the given point to 4
+            boundaries (left, top, right, bottom) with shape (n, 4).
+        max_shape (Optional[Tuple[int, int]]): Shape of the image (height, width) for clipping.
+
+    Returns:
+        np.ndarray: Decoded bounding boxes with shape (n, 4) as [x1, y1, x2, y2].
+    """
+    x1 = points[:, 0] - distance[:, 0]
+    y1 = points[:, 1] - distance[:, 1]
+    x2 = points[:, 0] + distance[:, 2]
+    y2 = points[:, 1] + distance[:, 3]
+
+    if max_shape is not None:
+        x1 = np.clip(x1, 0, max_shape[1])
+        y1 = np.clip(y1, 0, max_shape[0])
+        x2 = np.clip(x2, 0, max_shape[1])
+        y2 = np.clip(y2, 0, max_shape[0])
+    else:
+        x1 = np.maximum(x1, 0)
+        y1 = np.maximum(y1, 0)
+        x2 = np.maximum(x2, 0)
+        y2 = np.maximum(y2, 0)
+
+    return np.stack([x1, y1, x2, y2], axis=-1)
+
+
+def distance2kps(points: np.ndarray, distance: np.ndarray, max_shape: Optional[Tuple[int, int]] = None) -> np.ndarray:
+    """
+    Decode distance prediction to keypoints (SCRFD specific).
+
+    Args:
+        points (np.ndarray): Anchor points with shape (n, 2), [x, y].
+        distance (np.ndarray): Distance from the given point to keypoints with shape (n, 2k).
+        max_shape (Optional[Tuple[int, int]]): Shape of the image (height, width) for clipping.
+
+    Returns:
+        np.ndarray: Decoded keypoints with shape (n, 2k).
+    """
+    preds = []
+    for i in range(0, distance.shape[1], 2):
+        px = points[:, i % 2] + distance[:, i]
+        py = points[:, i % 2 + 1] + distance[:, i + 1]
+        if max_shape is not None:
+            px = np.clip(px, 0, max_shape[1])
+            py = np.clip(py, 0, max_shape[0])
+        preds.append(px)
+        preds.append(py)
+    return np.stack(preds, axis=-1)

uniface/constants.py

@@ -5,6 +5,7 @@
 from enum import Enum
 from typing import Dict
 
+
 # fmt: off
 class SphereFaceWeights(str, Enum):
     """
@@ -29,7 +30,7 @@ class ArcFaceWeights(str, Enum):
     Pretrained weights from ArcFace model (insightface).
     https://github.com/deepinsight/insightface
     """
-    MNET = "arcface_mnet"
+    MNET   = "arcface_mnet"
     RESNET = "arcface_resnet"
 
 class RetinaFaceWeights(str, Enum):
@@ -54,6 +55,22 @@ class SCRFDWeights(str, Enum):
     SCRFD_500M_KPS = "scrfd_500m"
 
 
+class YOLOv5FaceWeights(str, Enum):
+    """
+    Trained on WIDER FACE dataset.
+    Original implementation: https://github.com/deepcam-cn/yolov5-face
+    Exported to ONNX from: https://github.com/yakhyo/yolov5-face-onnx-inference
+
+    Model Performance (WIDER FACE):
+    - YOLOV5N: 11MB, 93.61% Easy / 91.52% Medium / 80.53% Hard
+    - YOLOV5S: 28MB, 94.33% Easy / 92.61% Medium / 83.15% Hard
+    - YOLOV5M: 82MB, 95.30% Easy / 93.76% Medium / 85.28% Hard
+    """
+    YOLOV5N = "yolov5n"
+    YOLOV5S = "yolov5s"
+    YOLOV5M = "yolov5m"
+
+
 class DDAMFNWeights(str, Enum):
     """
     Trained on AffectNet dataset.
@@ -78,87 +95,75 @@ class LandmarkWeights(str, Enum):
     """
     DEFAULT = "2d_106"
 
-# fmt: on
-
 
 MODEL_URLS: Dict[Enum, str] = {
-
     # RetinaFace
-    RetinaFaceWeights.MNET_025: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1_0.25.onnx',
-    RetinaFaceWeights.MNET_050: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1_0.50.onnx',
-    RetinaFaceWeights.MNET_V1:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv1.onnx',
-    RetinaFaceWeights.MNET_V2:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_mv2.onnx',
-    RetinaFaceWeights.RESNET18: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_r18.onnx',
-    RetinaFaceWeights.RESNET34: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/retinaface_r34.onnx',
-
+    RetinaFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.25.onnx',
+    RetinaFaceWeights.MNET_050:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.50.onnx',
+    RetinaFaceWeights.MNET_V1:       'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1.onnx',
+    RetinaFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv2.onnx',
+    RetinaFaceWeights.RESNET18:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r18.onnx',
+    RetinaFaceWeights.RESNET34:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r34.onnx',
     # MobileFace
-    MobileFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V3_SMALL: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    MobileFaceWeights.MNET_V3_LARGE: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-
+    MobileFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv1_0.25.onnx',
+    MobileFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv2.onnx',
+    MobileFaceWeights.MNET_V3_SMALL: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_small.onnx',
+    MobileFaceWeights.MNET_V3_LARGE: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_large.onnx',
     # SphereFace
-    SphereFaceWeights.SPHERE20: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-    SphereFaceWeights.SPHERE36: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/###',
-
-
+    SphereFaceWeights.SPHERE20:      'https://github.com/yakhyo/uniface/releases/download/weights/sphere20.onnx',
+    SphereFaceWeights.SPHERE36:      'https://github.com/yakhyo/uniface/releases/download/weights/sphere36.onnx',
     # ArcFace
-    ArcFaceWeights.MNET:   'https://github.com/yakhyo/uniface/releases/download/v0.1.2/w600k_mbf.onnx',
-    ArcFaceWeights.RESNET: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/w600k_r50.onnx',
-
+    ArcFaceWeights.MNET:             'https://github.com/yakhyo/uniface/releases/download/weights/w600k_mbf.onnx',
+    ArcFaceWeights.RESNET:           'https://github.com/yakhyo/uniface/releases/download/weights/w600k_r50.onnx',
     # SCRFD
-    SCRFDWeights.SCRFD_10G_KPS:  'https://github.com/yakhyo/uniface/releases/download/v0.1.2/scrfd_10g_kps.onnx',
-    SCRFDWeights.SCRFD_500M_KPS: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/scrfd_500m_kps.onnx',
-
-
+    SCRFDWeights.SCRFD_10G_KPS:      'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_10g_kps.onnx',
+    SCRFDWeights.SCRFD_500M_KPS:     'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_500m_kps.onnx',
+    # YOLOv5-Face
+    YOLOv5FaceWeights.YOLOV5N:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5n_face.onnx',
+    YOLOv5FaceWeights.YOLOV5S:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5s_face.onnx',
+    YOLOv5FaceWeights.YOLOV5M:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5m_face.onnx',
     # DDAFM
-    DDAMFNWeights.AFFECNET7: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/affecnet7.script',
-    DDAMFNWeights.AFFECNET8: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/affecnet8.script',
-
+    DDAMFNWeights.AFFECNET7:         'https://github.com/yakhyo/uniface/releases/download/weights/affecnet7.script',
+    DDAMFNWeights.AFFECNET8:         'https://github.com/yakhyo/uniface/releases/download/weights/affecnet8.script',
     # AgeGender
-    AgeGenderWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/genderage.onnx',
-
+    AgeGenderWeights.DEFAULT:        'https://github.com/yakhyo/uniface/releases/download/weights/genderage.onnx',
     # Landmarks
-    LandmarkWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/v0.1.2/2d106det.onnx',
+    LandmarkWeights.DEFAULT:         'https://github.com/yakhyo/uniface/releases/download/weights/2d106det.onnx',
 }
 
 MODEL_SHA256: Dict[Enum, str] = {
     # RetinaFace
-    RetinaFaceWeights.MNET_025: 'b7a7acab55e104dce6f32cdfff929bd83946da5cd869b9e2e9bdffafd1b7e4a5',
-    RetinaFaceWeights.MNET_050: 'd8977186f6037999af5b4113d42ba77a84a6ab0c996b17c713cc3d53b88bfc37',
-    RetinaFaceWeights.MNET_V1:  '75c961aaf0aff03d13c074e9ec656e5510e174454dd4964a161aab4fe5f04153',
-    RetinaFaceWeights.MNET_V2:  '3ca44c045651cabeed1193a1fae8946ad1f3a55da8fa74b341feab5a8319f757',
-    RetinaFaceWeights.RESNET18: 'e8b5ddd7d2c3c8f7c942f9f10cec09d8e319f78f09725d3f709631de34fb649d',
-    RetinaFaceWeights.RESNET34: 'bd0263dc2a465d32859555cb1741f2d98991eb0053696e8ee33fec583d30e630',
-
+    RetinaFaceWeights.MNET_025:      'b7a7acab55e104dce6f32cdfff929bd83946da5cd869b9e2e9bdffafd1b7e4a5',
+    RetinaFaceWeights.MNET_050:      'd8977186f6037999af5b4113d42ba77a84a6ab0c996b17c713cc3d53b88bfc37',
+    RetinaFaceWeights.MNET_V1:       '75c961aaf0aff03d13c074e9ec656e5510e174454dd4964a161aab4fe5f04153',
+    RetinaFaceWeights.MNET_V2:       '3ca44c045651cabeed1193a1fae8946ad1f3a55da8fa74b341feab5a8319f757',
+    RetinaFaceWeights.RESNET18:      'e8b5ddd7d2c3c8f7c942f9f10cec09d8e319f78f09725d3f709631de34fb649d',
+    RetinaFaceWeights.RESNET34:      'bd0263dc2a465d32859555cb1741f2d98991eb0053696e8ee33fec583d30e630',
     # MobileFace
-    MobileFaceWeights.MNET_025:      '#',
-    MobileFaceWeights.MNET_V2:       '#',
-    MobileFaceWeights.MNET_V3_SMALL: '#',
-    MobileFaceWeights.MNET_V3_LARGE: '#',
-
+    MobileFaceWeights.MNET_025:      'eeda7d23d9c2b40cf77fa8da8e895b5697465192648852216074679657f8ee8b',
+    MobileFaceWeights.MNET_V2:       '38b148284dd48cc898d5d4453104252fbdcbacc105fe3f0b80e78954d9d20d89',
+    MobileFaceWeights.MNET_V3_SMALL: 'd4acafa1039a82957aa8a9a1dac278a401c353a749c39df43de0e29cc1c127c3',
+    MobileFaceWeights.MNET_V3_LARGE: '0e48f8e11f070211716d03e5c65a3db35a5e917cfb5bc30552358629775a142a',
     # SphereFace
-    SphereFaceWeights.SPHERE20: '#',
-    SphereFaceWeights.SPHERE36: '#',
-
-
+    SphereFaceWeights.SPHERE20:      'c02878cf658eb1861f580b7e7144b0d27cc29c440bcaa6a99d466d2854f14c9d',
+    SphereFaceWeights.SPHERE36:      '13b3890cd5d7dec2b63f7c36fd7ce07403e5a0bbb701d9647c0289e6cbe7bb20',
     # ArcFace
-    ArcFaceWeights.MNET:   '9cc6e4a75f0e2bf0b1aed94578f144d15175f357bdc05e815e5c4a02b319eb4f',
-    ArcFaceWeights.RESNET: '4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43',
-
+    ArcFaceWeights.MNET:             '9cc6e4a75f0e2bf0b1aed94578f144d15175f357bdc05e815e5c4a02b319eb4f',
+    ArcFaceWeights.RESNET:           '4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43',
     # SCRFD
-    SCRFDWeights.SCRFD_10G_KPS:  '5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91',
-    SCRFDWeights.SCRFD_500M_KPS: '5e4447f50245bbd7966bd6c0fa52938c61474a04ec7def48753668a9d8b4ea3a',
-
+    SCRFDWeights.SCRFD_10G_KPS:      '5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91',
+    SCRFDWeights.SCRFD_500M_KPS:     '5e4447f50245bbd7966bd6c0fa52938c61474a04ec7def48753668a9d8b4ea3a',
+    # YOLOv5-Face
+    YOLOv5FaceWeights.YOLOV5N:       'eb244a06e36999db732b317c2b30fa113cd6cfc1a397eaf738f2d6f33c01f640',
+    YOLOv5FaceWeights.YOLOV5S:       'fc682801cd5880e1e296184a14aea0035486b5146ec1a1389d2e7149cb134bb2',
+    YOLOv5FaceWeights.YOLOV5M:       '04302ce27a15bde3e20945691b688e2dd018a10e92dd8932146bede6a49207b2',
     # DDAFM
-    DDAMFNWeights.AFFECNET7: '10535bf8b6afe8e9d6ae26cea6c3add9a93036e9addb6adebfd4a972171d015d',
-    DDAMFNWeights.AFFECNET8: '8c66963bc71db42796a14dfcbfcd181b268b65a3fc16e87147d6a3a3d7e0f487',
-
+    DDAMFNWeights.AFFECNET7:         '10535bf8b6afe8e9d6ae26cea6c3add9a93036e9addb6adebfd4a972171d015d',
+    DDAMFNWeights.AFFECNET8:         '8c66963bc71db42796a14dfcbfcd181b268b65a3fc16e87147d6a3a3d7e0f487',
     # AgeGender
-    AgeGenderWeights.DEFAULT: '4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb',
-
+    AgeGenderWeights.DEFAULT:        '4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb',
     # Landmark
-    LandmarkWeights.DEFAULT: 'f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf',
+    LandmarkWeights.DEFAULT:         'f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf',
 }
 
 CHUNK_SIZE = 8192

uniface/detection/__init__.py

@@ -3,12 +3,14 @@
 # GitHub: https://github.com/yakhyo
 
 
-import numpy as np
-from typing import Tuple, Dict, Any, List
+from typing import Any, Dict, List
+
+import numpy as np
 
-from .scrfd import SCRFD
 from .base import BaseDetector
 from .retinaface import RetinaFace
+from .scrfd import SCRFD
+from .yolov5 import YOLOv5Face
 
 # Global cache for detector instances
 _detector_cache: Dict[str, BaseDetector] = {}
@@ -20,7 +22,7 @@ def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> Lis
 
     Args:
         image (np.ndarray): Input image as numpy array.
-        method (str): Detection method to use. Options: 'retinaface', 'scrfd'.
+        method (str): Detection method to use. Options: 'retinaface', 'scrfd', 'yolov5face'.
         **kwargs: Additional arguments passed to the detector.
 
     Returns:
@@ -38,9 +40,9 @@ def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> Lis
         ...     print(f"BBox: {face['bbox']}")
     """
     method_name = method.lower()
-    
+
     sorted_kwargs = sorted(kwargs.items())
-    cache_key = f"{method_name}_{str(sorted_kwargs)}"
+    cache_key = f'{method_name}_{str(sorted_kwargs)}'
 
     if cache_key not in _detector_cache:
         # Pass kwargs to create the correctly configured detector
@@ -58,6 +60,7 @@ def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
         method (str): Detection method. Options:
             - 'retinaface': RetinaFace detector (default)
             - 'scrfd': SCRFD detector (fast and accurate)
+            - 'yolov5face': YOLOv5-Face detector (accurate with landmarks)
         **kwargs: Detector-specific parameters
 
     Returns:
@@ -85,6 +88,14 @@ def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
         ...     conf_thresh=0.8,
         ...     nms_thresh=0.4
         ... )
+
+        >>> # YOLOv5-Face detector
+        >>> detector = create_detector(
+        ...     'yolov5face',
+        ...     model_name=YOLOv5FaceWeights.YOLOV5S,
+        ...     conf_thresh=0.25,
+        ...     nms_thresh=0.45
+        ... )
     """
     method = method.lower()
 
@@ -94,12 +105,12 @@ def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
     elif method == 'scrfd':
         return SCRFD(**kwargs)
 
+    elif method == 'yolov5face':
+        return YOLOv5Face(**kwargs)
+
     else:
-        available_methods = ['retinaface', 'scrfd']
-        raise ValueError(
-            f"Unsupported detection method: '{method}'. "
-            f"Available methods: {available_methods}"
-        )
+        available_methods = ['retinaface', 'scrfd', 'yolov5face']
+        raise ValueError(f"Unsupported detection method: '{method}'. Available methods: {available_methods}")
 
 
 def list_available_detectors() -> Dict[str, Dict[str, Any]]:
@@ -118,8 +129,8 @@ def list_available_detectors() -> Dict[str, Dict[str, Any]]:
                 'model_name': 'mnet_v2',
                 'conf_thresh': 0.5,
                 'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
+                'input_size': (640, 640),
+            },
         },
         'scrfd': {
             'description': 'SCRFD detector - fast and accurate with efficient architecture',
@@ -129,9 +140,20 @@ def list_available_detectors() -> Dict[str, Dict[str, Any]]:
                 'model_name': 'scrfd_10g_kps',
                 'conf_thresh': 0.5,
                 'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
-        }
+                'input_size': (640, 640),
+            },
+        },
+        'yolov5face': {
+            'description': 'YOLOv5-Face detector - accurate face detection with landmarks',
+            'supports_landmarks': True,
+            'paper': 'https://arxiv.org/abs/2105.12931',
+            'default_params': {
+                'model_name': 'yolov5s_face',
+                'conf_thresh': 0.25,
+                'nms_thresh': 0.45,
+                'input_size': 640,
+            },
+        },
     }
 
 
@@ -141,5 +163,6 @@ __all__ = [
     'list_available_detectors',
     'SCRFD',
     'RetinaFace',
+    'YOLOv5Face',
     'BaseDetector',
 ]

uniface/detection/base.py

@@ -2,13 +2,10 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""
-Base classes for face detection.
-"""
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List
 
 import numpy as np
-from abc import ABC, abstractmethod
-from typing import Tuple, Dict, Any
 
 
 class BaseDetector(ABC):
@@ -24,7 +21,7 @@ class BaseDetector(ABC):
         self.config = kwargs
 
     @abstractmethod
-    def detect(self, image: np.ndarray, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
+    def detect(self, image: np.ndarray, **kwargs) -> List[Dict[str, Any]]:
         """
         Detect faces in an image.
 
@@ -33,11 +30,18 @@ class BaseDetector(ABC):
             **kwargs: Additional detection parameters
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: (detections, landmarks)
-                - detections: Bounding boxes with confidence scores, shape (N, 5)
-                  Format: [x_min, y_min, x_max, y_max, confidence]
-                - landmarks: Facial landmark points, shape (N, 5, 2) for 5-point landmarks
-                  or (N, 68, 2) for 68-point landmarks. Empty array if not supported.
+            List[Dict[str, Any]]: List of detected faces, where each dictionary contains:
+                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
+                - 'landmarks' (np.ndarray): Facial landmarks with shape (5, 2) for 5-point landmarks
+                  or (68, 2) for 68-point landmarks. Empty array if not supported.
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
+            ...     confidence = face['confidence']  # float
+            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
         """
         pass
 
@@ -55,7 +59,7 @@ class BaseDetector(ABC):
         pass
 
     @abstractmethod
-    def postprocess(self, outputs, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
+    def postprocess(self, outputs, **kwargs) -> Any:
         """
         Postprocess model outputs to get final detections.
 
@@ -64,13 +68,13 @@ class BaseDetector(ABC):
             **kwargs: Additional postprocessing parameters
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: (detections, landmarks)
+            Any: Processed outputs (implementation-specific format, typically tuple of arrays)
         """
         pass
 
     def __str__(self) -> str:
         """String representation of the detector."""
-        return f"{self.__class__.__name__}({self.config})"
+        return f'{self.__class__.__name__}({self.config})'
 
     def __repr__(self) -> str:
         """Detailed string representation."""
@@ -96,5 +100,5 @@ class BaseDetector(ABC):
         return {
             'name': self.__class__.__name__,
             'supports_landmarks': self._supports_landmarks,
-            'config': self.config
+            'config': self.config,
         }

uniface/detection/retinaface.py

@@ -2,23 +2,23 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from typing import Any, Dict, List, Literal, Tuple
+
 import numpy as np
 
-from typing import Tuple, List, Literal, Dict, Any
-
+from uniface.common import (
+    decode_boxes,
+    decode_landmarks,
+    generate_anchors,
+    non_max_suppression,
+    resize_image,
+)
+from uniface.constants import RetinaFaceWeights
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
-from uniface.constants import RetinaFaceWeights
 from uniface.onnx_utils import create_onnx_session
 
 from .base import BaseDetector
-from .utils import (
-    non_max_supression,
-    resize_image,
-    decode_boxes,
-    generate_anchors,
-    decode_landmarks
-)
 
 
 class RetinaFace(BaseDetector):
@@ -27,16 +27,19 @@ class RetinaFace(BaseDetector):
 
     Title: "RetinaFace: Single-stage Dense Face Localisation in the Wild"
     Paper: https://arxiv.org/abs/1905.00641
+    Code: https://github.com/yakhyo/retinaface-pytorch
 
     Args:
-        **kwargs: Keyword arguments passed to BaseDetector and RetinaFace. Supported keys include:
-            model_name (RetinaFaceWeights, optional): Model weights to use. Defaults to `RetinaFaceWeights.MNET_V2`.
-            conf_thresh (float, optional): Confidence threshold for filtering detections. Defaults to 0.5.
-            nms_thresh (float, optional): Non-maximum suppression (NMS) IoU threshold. Defaults to 0.4.
-            pre_nms_topk (int, optional): Number of top-scoring boxes considered before NMS. Defaults to 5000.
-            post_nms_topk (int, optional): Max number of detections kept after NMS. Defaults to 750.
-            dynamic_size (bool, optional): If True, generate anchors dynamically per input image. Defaults to False.
-            input_size (Tuple[int, int], optional): Fixed input size (width, height) if `dynamic_size=False`. Defaults to (640, 640).
+        model_name (RetinaFaceWeights): Model weights to use. Defaults to `RetinaFaceWeights.MNET_V2`.
+        conf_thresh (float): Confidence threshold for filtering detections. Defaults to 0.5.
+        nms_thresh (float): Non-maximum suppression (NMS) IoU threshold. Defaults to 0.4.
+        input_size (Tuple[int, int]): Fixed input size (width, height) if `dynamic_size=False`.
+            Defaults to (640, 640).
+            Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        **kwargs: Advanced options:
+            pre_nms_topk (int): Number of top-scoring boxes considered before NMS. Defaults to 5000.
+            post_nms_topk (int): Max number of detections kept after NMS. Defaults to 750.
+            dynamic_size (bool): If True, generate anchors dynamically per input image. Defaults to False.
 
     Attributes:
         model_name (RetinaFaceWeights): Selected model variant.
@@ -55,31 +58,47 @@ class RetinaFace(BaseDetector):
         RuntimeError: If the ONNX model fails to load or initialize.
     """
 
-    def __init__(self, **kwargs) -> None:
-        super().__init__(**kwargs)
+    def __init__(
+        self,
+        *,
+        model_name: RetinaFaceWeights = RetinaFaceWeights.MNET_V2,
+        conf_thresh: float = 0.5,
+        nms_thresh: float = 0.4,
+        input_size: Tuple[int, int] = (640, 640),
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            conf_thresh=conf_thresh,
+            nms_thresh=nms_thresh,
+            input_size=input_size,
+            **kwargs,
+        )
         self._supports_landmarks = True  # RetinaFace supports landmarks
 
-        self.model_name = kwargs.get('model_name', RetinaFaceWeights.MNET_V2)
-        self.conf_thresh = kwargs.get('conf_thresh', 0.5)
-        self.nms_thresh = kwargs.get('nms_thresh', 0.4)
+        self.model_name = model_name
+        self.conf_thresh = conf_thresh
+        self.nms_thresh = nms_thresh
+        self.input_size = input_size
+
+        # Advanced options from kwargs
         self.pre_nms_topk = kwargs.get('pre_nms_topk', 5000)
         self.post_nms_topk = kwargs.get('post_nms_topk', 750)
         self.dynamic_size = kwargs.get('dynamic_size', False)
-        self.input_size = kwargs.get('input_size', (640, 640))
 
         Logger.info(
-            f"Initializing RetinaFace with model={self.model_name}, conf_thresh={self.conf_thresh}, nms_thresh={self.nms_thresh}, "
-            f"input_size={self.input_size}"
+            f'Initializing RetinaFace with model={self.model_name}, conf_thresh={self.conf_thresh}, '
+            f'nms_thresh={self.nms_thresh}, input_size={self.input_size}'
         )
 
         # Get path to model weights
         self._model_path = verify_model_weights(self.model_name)
-        Logger.info(f"Verified model weights located at: {self._model_path}")
+        Logger.info(f'Verified model weights located at: {self._model_path}')
 
         # Precompute anchors if using static size
         if not self.dynamic_size and self.input_size is not None:
             self._priors = generate_anchors(image_size=self.input_size)
-            Logger.debug("Generated anchors for static input size.")
+            Logger.debug('Generated anchors for static input size.')
 
         # Initialize model
         self._initialize_model(self._model_path)
@@ -98,7 +117,7 @@ class RetinaFace(BaseDetector):
             self.session = create_onnx_session(model_path)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized the model from {model_path}")
+            Logger.info(f'Successfully initialized the model from {model_path}')
         except Exception as e:
             Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
             raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
@@ -131,9 +150,10 @@ class RetinaFace(BaseDetector):
     def detect(
         self,
         image: np.ndarray,
+        *,
         max_num: int = 0,
-        metric: Literal["default", "max"] = "max",
-        center_weight: float = 2.0
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
     ) -> List[Dict[str, Any]]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
@@ -149,9 +169,18 @@ class RetinaFace(BaseDetector):
 
         Returns:
             List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox': [x1, y1, x2, y2] - Bounding box coordinates
-                - 'confidence': float - Detection confidence score
-                - 'landmarks': [[x1, y1], [x2, y2], [x3, y3], [x4, y4], [x5, y5]] - 5-point facial landmarks
+                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
+                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
+            ...     confidence = face['confidence']  # float
+            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
         """
 
         original_height, original_width = image.shape[:2]
@@ -178,10 +207,12 @@ class RetinaFace(BaseDetector):
 
             # Calculate offsets from image center
             center = (original_height // 2, original_width // 2)
-            offsets = np.vstack([
-                (detections[:, 0] + detections[:, 2]) / 2 - center[1],
-                (detections[:, 1] + detections[:, 3]) / 2 - center[0]
-            ])
+            offsets = np.vstack(
+                [
+                    (detections[:, 0] + detections[:, 2]) / 2 - center[1],
+                    (detections[:, 1] + detections[:, 3]) / 2 - center[0],
+                ]
+            )
             offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
 
             # Calculate scores based on the chosen metric
@@ -199,15 +230,17 @@ class RetinaFace(BaseDetector):
         faces = []
         for i in range(detections.shape[0]):
             face_dict = {
-                'bbox': detections[i, :4].astype(float).tolist(),
-                'confidence': detections[i, 4].item(),
-                'landmarks': landmarks[i].astype(float).tolist()
+                'bbox': detections[i, :4],
+                'confidence': float(detections[i, 4]),
+                'landmarks': landmarks[i],
             }
             faces.append(face_dict)
 
         return faces
 
-    def postprocess(self, outputs: List[np.ndarray], resize_factor: float, shape: Tuple[int, int]) -> Tuple[np.ndarray, np.ndarray]:
+    def postprocess(
+        self, outputs: List[np.ndarray], resize_factor: float, shape: Tuple[int, int]
+    ) -> Tuple[np.ndarray, np.ndarray]:
         """
         Process the model outputs into final detection results.
 
@@ -226,7 +259,11 @@ class RetinaFace(BaseDetector):
                 - landmarks (np.ndarray): Array of detected facial landmarks.
                 Shape: (num_detections, 5, 2), where each row contains 5 landmark points (x, y).
         """
-        loc, conf, landmarks = outputs[0].squeeze(0), outputs[1].squeeze(0), outputs[2].squeeze(0)
+        loc, conf, landmarks = (
+            outputs[0].squeeze(0),
+            outputs[1].squeeze(0),
+            outputs[2].squeeze(0),
+        )
 
         # Decode boxes and landmarks
         boxes = decode_boxes(loc, self._priors)
@@ -242,22 +279,31 @@ class RetinaFace(BaseDetector):
         boxes, landmarks, scores = boxes[mask], landmarks[mask], scores[mask]
 
         # Sort by scores
-        order = scores.argsort()[::-1][:self.pre_nms_topk]
+        order = scores.argsort()[::-1][: self.pre_nms_topk]
         boxes, landmarks, scores = boxes[order], landmarks[order], scores[order]
 
         # Apply NMS
         detections = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
-        keep = non_max_supression(detections, self.nms_thresh)
+        keep = non_max_suppression(detections, self.nms_thresh)
         detections, landmarks = detections[keep], landmarks[keep]
 
         # Keep top-k detections
-        detections, landmarks = detections[:self.post_nms_topk], landmarks[:self.post_nms_topk]
+        detections, landmarks = (
+            detections[: self.post_nms_topk],
+            landmarks[: self.post_nms_topk],
+        )
 
-        landmarks = landmarks.reshape(-1, 5, 2).astype(np.int32)
+        landmarks = landmarks.reshape(-1, 5, 2).astype(np.float32)
 
         return detections, landmarks
 
-    def _scale_detections(self, boxes: np.ndarray, landmarks: np.ndarray, resize_factor: float, shape: Tuple[int, int]) -> Tuple[np.ndarray, np.ndarray]:
+    def _scale_detections(
+        self,
+        boxes: np.ndarray,
+        landmarks: np.ndarray,
+        resize_factor: float,
+        shape: Tuple[int, int],
+    ) -> Tuple[np.ndarray, np.ndarray]:
         # Scale bounding boxes and landmarks to the original image size.
         bbox_scale = np.array([shape[0], shape[1]] * 2)
         boxes = boxes * bbox_scale / resize_factor
@@ -272,30 +318,31 @@ class RetinaFace(BaseDetector):
 def draw_bbox(frame, bbox, score, color=(0, 255, 0), thickness=2):
     x1, y1, x2, y2 = map(int, bbox)  # Unpack 4 bbox values
     cv2.rectangle(frame, (x1, y1), (x2, y2), color, thickness)
-    cv2.putText(frame, f"{score:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
+    cv2.putText(frame, f'{score:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
 
 
 def draw_keypoints(frame, points, color=(0, 0, 255), radius=2):
-    for (x, y) in points.astype(np.int32):
+    for x, y in points.astype(np.int32):
         cv2.circle(frame, (int(x), int(y)), radius, color, -1)
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     import cv2
+
     detector = RetinaFace(model_name=RetinaFaceWeights.MNET_050)
     print(detector.get_info())
     cap = cv2.VideoCapture(0)
 
     if not cap.isOpened():
-        print("❌ Failed to open webcam.")
+        print('Failed to open webcam.')
         exit()
 
-    print("📷 Webcam started. Press 'q' to exit.")
+    print("Webcam started. Press 'q' to exit.")
 
     while True:
         ret, frame = cap.read()
         if not ret:
-            print("❌ Failed to read frame.")
+            print('Failed to read frame.')
             break
 
         # Get face detections as list of dictionaries
@@ -318,11 +365,18 @@ if __name__ == "__main__":
                 draw_keypoints(frame, points)
 
         # Display face count
-        cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.7,
+            (255, 255, 255),
+            2,
+        )
 
-        cv2.imshow("FaceDetection", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
+        cv2.imshow('FaceDetection', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 
     cap.release()

uniface/detection/scrfd.py

@@ -7,15 +7,15 @@ from typing import Any, Dict, List, Literal, Tuple
 import cv2
 import numpy as np
 
+from uniface.common import distance2bbox, distance2kps, non_max_suppression, resize_image
 from uniface.constants import SCRFDWeights
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
 
 from .base import BaseDetector
-from .utils import distance2bbox, distance2kps, non_max_supression, resize_image
 
-__all__ = ["SCRFD"]
+__all__ = ['SCRFD']
 
 
 class SCRFD(BaseDetector):
@@ -24,16 +24,20 @@ class SCRFD(BaseDetector):
 
     Title: "Sample and Computation Redistribution for Efficient Face Detection"
     Paper: https://arxiv.org/abs/2105.04714
+    Code: https://github.com/insightface/insightface
 
     Args:
-        **kwargs: Keyword arguments passed to BaseDetector and SCRFD. Supported keys include:
-            model_name (SCRFDWeights, optional): Predefined model enum (e.g., `SCRFD_10G_KPS`).
-                Specifies the SCRFD variant to load. Defaults to SCRFD_10G_KPS.
-            conf_thresh (float, optional): Confidence threshold for filtering detections. Defaults to 0.5.
-            nms_thresh (float, optional): Non-Maximum Suppression threshold. Defaults to 0.4.
-            input_size (Tuple[int, int], optional): Input image size (width, height). Defaults to (640, 640).
+        model_name (SCRFDWeights): Predefined model enum (e.g., `SCRFD_10G_KPS`).
+            Specifies the SCRFD variant to load. Defaults to SCRFD_10G_KPS.
+        conf_thresh (float): Confidence threshold for filtering detections. Defaults to 0.5.
+        nms_thresh (float): Non-Maximum Suppression threshold. Defaults to 0.4.
+        input_size (Tuple[int, int]): Input image size (width, height).
+            Defaults to (640, 640).
+            Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        **kwargs: Reserved for future advanced options.
 
     Attributes:
+        model_name (SCRFDWeights): Selected model variant.
         conf_thresh (float): Threshold used to filter low-confidence detections.
         nms_thresh (float): Threshold used during NMS to suppress overlapping boxes.
         input_size (Tuple[int, int]): Image size to which inputs are resized before inference.
@@ -48,15 +52,25 @@ class SCRFD(BaseDetector):
         RuntimeError: If the ONNX model fails to load or initialize.
     """
 
-    def __init__(self, **kwargs) -> None:
-        super().__init__(**kwargs)
+    def __init__(
+        self,
+        *,
+        model_name: SCRFDWeights = SCRFDWeights.SCRFD_10G_KPS,
+        conf_thresh: float = 0.5,
+        nms_thresh: float = 0.4,
+        input_size: Tuple[int, int] = (640, 640),
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            conf_thresh=conf_thresh,
+            nms_thresh=nms_thresh,
+            input_size=input_size,
+            **kwargs,
+        )
         self._supports_landmarks = True  # SCRFD supports landmarks
 
-        model_name = kwargs.get("model_name", SCRFDWeights.SCRFD_10G_KPS)
-        conf_thresh = kwargs.get("conf_thresh", 0.5)
-        nms_thresh = kwargs.get("nms_thresh", 0.4)
-        input_size = kwargs.get("input_size", (640, 640))
-
+        self.model_name = model_name
         self.conf_thresh = conf_thresh
         self.nms_thresh = nms_thresh
         self.input_size = input_size
@@ -69,13 +83,13 @@ class SCRFD(BaseDetector):
         # ---------------------------------
 
         Logger.info(
-            f"Initializing SCRFD with model={model_name}, conf_thresh={conf_thresh}, nms_thresh={nms_thresh}, "
-            f"input_size={input_size}"
+            f'Initializing SCRFD with model={self.model_name}, conf_thresh={self.conf_thresh}, '
+            f'nms_thresh={self.nms_thresh}, input_size={self.input_size}'
         )
 
         # Get path to model weights
-        self._model_path = verify_model_weights(model_name)
-        Logger.info(f"Verified model weights located at: {self._model_path}")
+        self._model_path = verify_model_weights(self.model_name)
+        Logger.info(f'Verified model weights located at: {self._model_path}')
 
         # Initialize model
         self._initialize_model(self._model_path)
@@ -94,7 +108,7 @@ class SCRFD(BaseDetector):
             self.session = create_onnx_session(model_path)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized the model from {model_path}")
+            Logger.info(f'Successfully initialized the model from {model_path}')
         except Exception as e:
             Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
             raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
@@ -173,7 +187,12 @@ class SCRFD(BaseDetector):
         return scores_list, bboxes_list, kpss_list
 
     def detect(
-        self, image: np.ndarray, max_num: int = 0, metric: Literal["default", "max"] = "max", center_weight: float = 2
+        self,
+        image: np.ndarray,
+        *,
+        max_num: int = 0,
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
     ) -> List[Dict[str, Any]]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
@@ -189,9 +208,18 @@ class SCRFD(BaseDetector):
 
         Returns:
             List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox': [x1, y1, x2, y2] - Bounding box coordinates
-                - 'confidence': float - Detection confidence score
-                - 'landmarks': [[x1, y1], [x2, y2], [x3, y3], [x4, y4], [x5, y5]] - 5-point facial landmarks
+                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
+                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
+            ...     confidence = face['confidence']  # float
+            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
         """
 
         original_height, original_width = image.shape[:2]
@@ -219,11 +247,11 @@ class SCRFD(BaseDetector):
         pre_det = np.hstack((bboxes, scores)).astype(np.float32, copy=False)
         pre_det = pre_det[order, :]
 
-        keep = non_max_supression(pre_det, threshold=self.nms_thresh)
+        keep = non_max_suppression(pre_det, threshold=self.nms_thresh)
 
         detections = pre_det[keep, :]
         landmarks = landmarks[order, :, :]
-        landmarks = landmarks[keep, :, :].astype(np.int32)
+        landmarks = landmarks[keep, :, :].astype(np.float32)
 
         if 0 < max_num < detections.shape[0]:
             # Calculate area of detections
@@ -240,7 +268,7 @@ class SCRFD(BaseDetector):
 
             # Calculate scores based on the chosen metric
             offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
-            if metric == "max":
+            if metric == 'max':
                 values = area
             else:
                 values = area - offset_dist_squared * center_weight
@@ -253,9 +281,9 @@ class SCRFD(BaseDetector):
         faces = []
         for i in range(detections.shape[0]):
             face_dict = {
-                "bbox": detections[i, :4].astype(float).tolist(),
-                "confidence": detections[i, 4].item(),
-                "landmarks": landmarks[i].astype(float).tolist(),
+                'bbox': detections[i, :4],
+                'confidence': float(detections[i, 4]),
+                'landmarks': landmarks[i],
             }
             faces.append(face_dict)
 
@@ -266,7 +294,7 @@ class SCRFD(BaseDetector):
 def draw_bbox(frame, bbox, score, color=(0, 255, 0), thickness=2):
     x1, y1, x2, y2 = map(int, bbox)  # Unpack 4 bbox values
     cv2.rectangle(frame, (x1, y1), (x2, y2), color, thickness)
-    cv2.putText(frame, f"{score:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
+    cv2.putText(frame, f'{score:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
 
 
 def draw_keypoints(frame, points, color=(0, 0, 255), radius=2):
@@ -274,21 +302,21 @@ def draw_keypoints(frame, points, color=(0, 0, 255), radius=2):
         cv2.circle(frame, (int(x), int(y)), radius, color, -1)
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     detector = SCRFD(model_name=SCRFDWeights.SCRFD_500M_KPS)
     print(detector.get_info())
     cap = cv2.VideoCapture(0)
 
     if not cap.isOpened():
-        print("❌ Failed to open webcam.")
+        print('Failed to open webcam.')
         exit()
 
-    print("📷 Webcam started. Press 'q' to exit.")
+    print("Webcam started. Press 'q' to exit.")
 
     while True:
         ret, frame = cap.read()
         if not ret:
-            print("❌ Failed to read frame.")
+            print('Failed to read frame.')
             break
 
         # Get face detections as list of dictionaries
@@ -297,9 +325,9 @@ if __name__ == "__main__":
         # Process each detected face
         for face in faces:
             # Extract bbox and landmarks from dictionary
-            bbox = face["bbox"]  # [x1, y1, x2, y2]
-            landmarks = face["landmarks"]  # [[x1, y1], [x2, y2], ...]
-            confidence = face["confidence"]
+            bbox = face['bbox']  # [x1, y1, x2, y2]
+            landmarks = face['landmarks']  # [[x1, y1], [x2, y2], ...]
+            confidence = face['confidence']
 
             # Pass bbox and confidence separately
             draw_bbox(frame, bbox, confidence)
@@ -311,10 +339,18 @@ if __name__ == "__main__":
                 draw_keypoints(frame, points)
 
         # Display face count
-        cv2.putText(frame, f"Faces: {len(faces)}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
+        cv2.putText(
+            frame,
+            f'Faces: {len(faces)}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.7,
+            (255, 255, 255),
+            2,
+        )
 
-        cv2.imshow("FaceDetection", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
+        cv2.imshow('FaceDetection', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 
     cap.release()

uniface/detection/utils.py

@@ -1,232 +0,0 @@
-# Copyright 2025 Yakhyokhuja Valikhujaev
-# Author: Yakhyokhuja Valikhujaev
-# GitHub: https://github.com/yakhyo
-
-import cv2
-import math
-import itertools
-import numpy as np
-
-from typing import Tuple, List
-
-
-def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
-    """
-    Resize an image to fit within a target shape while keeping its aspect ratio.
-
-    Args:
-        frame (np.ndarray): Input image.
-        target_shape (Tuple[int, int]): Target size (width, height). Defaults to (640, 640).
-
-    Returns:
-        Tuple[np.ndarray, float]: Resized image on a blank canvas and the resize factor.
-    """
-    width, height = target_shape
-
-    # Aspect-ratio preserving resize
-    im_ratio = float(frame.shape[0]) / frame.shape[1]
-    model_ratio = height / width
-    if im_ratio > model_ratio:
-        new_height = height
-        new_width = int(new_height / im_ratio)
-    else:
-        new_width = width
-        new_height = int(new_width * im_ratio)
-
-    resize_factor = float(new_height) / frame.shape[0]
-    resized_frame = cv2.resize(frame, (new_width, new_height))
-
-    # Create blank image and place resized image on it
-    image = np.zeros((height, width, 3), dtype=np.uint8)
-    image[:new_height, :new_width, :] = resized_frame
-
-    return image, resize_factor
-
-
-def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
-    """
-    Generate anchor boxes for a given image size.
-
-    Args:
-        image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640).
-
-    Returns:
-        np.ndarray: Anchor box coordinates as a NumPy array.
-    """
-    image_size = image_size
-
-    steps = [8, 16, 32]
-    min_sizes = [[16, 32], [64, 128], [256, 512]]
-
-    anchors = []
-    feature_maps = [
-        [
-            math.ceil(image_size[0] / step),
-            math.ceil(image_size[1] / step)
-        ] for step in steps
-    ]
-
-    for k, (map_height, map_width) in enumerate(feature_maps):
-        step = steps[k]
-        for i, j in itertools.product(range(map_height), range(map_width)):
-            for min_size in min_sizes[k]:
-                s_kx = min_size / image_size[1]
-                s_ky = min_size / image_size[0]
-
-                dense_cx = [x * step / image_size[1] for x in [j + 0.5]]
-                dense_cy = [y * step / image_size[0] for y in [i + 0.5]]
-                for cy, cx in itertools.product(dense_cy, dense_cx):
-                    anchors += [cx, cy, s_kx, s_ky]
-
-    output = np.array(anchors, dtype=np.float32).reshape(-1, 4)
-    return output
-
-
-def non_max_supression(dets: List[np.ndarray], threshold: float):
-    """
-    Apply Non-Maximum Suppression (NMS) to reduce overlapping bounding boxes based on a threshold.
-
-    Args:
-        dets (numpy.ndarray): Array of detections with each row as [x1, y1, x2, y2, score].
-        threshold (float): IoU threshold for suppression.
-
-    Returns:
-        list: Indices of bounding boxes retained after suppression.
-    """
-    x1 = dets[:, 0]
-    y1 = dets[:, 1]
-    x2 = dets[:, 2]
-    y2 = dets[:, 3]
-    scores = dets[:, 4]
-
-    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
-    order = scores.argsort()[::-1]
-
-    keep = []
-    while order.size > 0:
-        i = order[0]
-        keep.append(i)
-        xx1 = np.maximum(x1[i], x1[order[1:]])
-        yy1 = np.maximum(y1[i], y1[order[1:]])
-        xx2 = np.minimum(x2[i], x2[order[1:]])
-        yy2 = np.minimum(y2[i], y2[order[1:]])
-
-        w = np.maximum(0.0, xx2 - xx1 + 1)
-        h = np.maximum(0.0, yy2 - yy1 + 1)
-        inter = w * h
-        ovr = inter / (areas[i] + areas[order[1:]] - inter)
-
-        inds = np.where(ovr <= threshold)[0]
-        order = order[inds + 1]
-
-    return keep
-
-
-def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode locations from predictions using priors to undo
-    the encoding done for offset regression at train time.
-
-    Args:
-        loc (np.ndarray): Location predictions for loc layers, shape: [num_priors, 4]
-        priors (np.ndarray): Prior boxes in center-offset form, shape: [num_priors, 4]
-        variances (list[float]): Variances of prior boxes
-
-    Returns:
-        np.ndarray: Decoded bounding box predictions
-    """
-    # Compute centers of predicted boxes
-    cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:]
-
-    # Compute widths and heights of predicted boxes
-    wh = priors[:, 2:] * np.exp(loc[:, 2:] * variances[1])
-
-    # Convert center, size to corner coordinates
-    boxes = np.zeros_like(loc)
-    boxes[:, :2] = cxcy - wh / 2  # xmin, ymin
-    boxes[:, 2:] = cxcy + wh / 2  # xmax, ymax
-
-    return boxes
-
-
-def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode landmark predictions using prior boxes.
-
-    Args:
-        predictions (np.ndarray): Landmark predictions, shape: [num_priors, 10]
-        priors (np.ndarray): Prior boxes, shape: [num_priors, 4]
-        variances (list): Scaling factors for landmark offsets.
-
-    Returns:
-        np.ndarray: Decoded landmarks, shape: [num_priors, 10]
-    """
-
-    # Reshape predictions to [num_priors, 5, 2] to process landmark points
-    predictions = predictions.reshape(predictions.shape[0], 5, 2)
-
-    # Expand priors to match (num_priors, 5, 2)
-    priors_xy = np.repeat(priors[:, :2][:, np.newaxis, :], 5, axis=1)  # (num_priors, 5, 2)
-    priors_wh = np.repeat(priors[:, 2:][:, np.newaxis, :], 5, axis=1)  # (num_priors, 5, 2)
-
-    # Compute absolute landmark positions
-    landmarks = priors_xy + predictions * variances[0] * priors_wh
-
-    # Flatten back to [num_priors, 10]
-    landmarks = landmarks.reshape(landmarks.shape[0], -1)
-
-    return landmarks
-
-
-def distance2bbox(points, distance, max_shape=None):
-    """Decode distance prediction to bounding box.
-
-    Args:
-        points (Tensor): Shape (n, 2), [x, y].
-        distance (Tensor): Distance from the given point to 4
-            boundaries (left, top, right, bottom).
-        max_shape (tuple): Shape of the image.
-
-    Returns:
-        Tensor: Decoded bounding boxes with shape (n, 4).
-    """
-    x1 = points[:, 0] - distance[:, 0]
-    y1 = points[:, 1] - distance[:, 1]
-    x2 = points[:, 0] + distance[:, 2]
-    y2 = points[:, 1] + distance[:, 3]
-    if max_shape is not None:
-        x1 = x1.clamp(min=0, max=max_shape[1])
-        y1 = y1.clamp(min=0, max=max_shape[0])
-        x2 = x2.clamp(min=0, max=max_shape[1])
-        y2 = y2.clamp(min=0, max=max_shape[0])
-    else:
-        x1 = np.maximum(x1, 0)
-        y1 = np.maximum(y1, 0)
-        x2 = np.maximum(x2, 0)
-        y2 = np.maximum(y2, 0)
-
-    return np.stack([x1, y1, x2, y2], axis=-1)
-
-
-def distance2kps(points, distance, max_shape=None):
-    """Decode distance prediction to keypoints.
-
-    Args:
-        points (Tensor): Shape (n, 2), [x, y].
-        distance (Tensor): Distance from the given point to 4
-            boundaries (left, top, right, bottom).
-        max_shape (tuple): Shape of the image.
-
-    Returns:
-        Tensor: Decoded keypoints with shape (n, 2k).
-    """
-    preds = []
-    for i in range(0, distance.shape[1], 2):
-        px = points[:, i % 2] + distance[:, i]
-        py = points[:, i % 2 + 1] + distance[:, i + 1]
-        if max_shape is not None:
-            px = px.clamp(min=0, max=max_shape[1])
-            py = py.clamp(min=0, max=max_shape[0])
-        preds.append(px)
-        preds.append(py)
-    return np.stack(preds, axis=-1)

uniface/detection/yolov5.py

@@ -0,0 +1,340 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import Any, Dict, List, Literal, Tuple
+
+import cv2
+import numpy as np
+
+from uniface.common import non_max_suppression
+from uniface.constants import YOLOv5FaceWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+
+from .base import BaseDetector
+
+__all__ = ['YOLOv5Face']
+
+
+class YOLOv5Face(BaseDetector):
+    """
+    Face detector based on the YOLOv5-Face architecture.
+
+    Title: "YOLO5Face: Why Reinventing a Face Detector"
+    Paper: https://arxiv.org/abs/2105.12931
+    Code: https://github.com/yakhyo/yolov5-face-onnx-inference (ONNX inference implementation)
+
+    Args:
+        model_name (YOLOv5FaceWeights): Predefined model enum (e.g., `YOLOV5S`).
+            Specifies the YOLOv5-Face variant to load. Defaults to YOLOV5S.
+        conf_thresh (float): Confidence threshold for filtering detections. Defaults to 0.6.
+        nms_thresh (float): Non-Maximum Suppression threshold. Defaults to 0.5.
+        input_size (int): Input image size. Defaults to 640.
+            Note: ONNX model is fixed at 640. Changing this will cause inference errors.
+        **kwargs: Advanced options:
+            max_det (int): Maximum number of detections to return. Defaults to 750.
+
+    Attributes:
+        model_name (YOLOv5FaceWeights): Selected model variant.
+        conf_thresh (float): Threshold used to filter low-confidence detections.
+        nms_thresh (float): Threshold used during NMS to suppress overlapping boxes.
+        input_size (int): Image size to which inputs are resized before inference.
+        max_det (int): Maximum number of detections to return.
+        _model_path (str): Absolute path to the downloaded/verified model weights.
+
+    Raises:
+        ValueError: If the model weights are invalid or not found.
+        RuntimeError: If the ONNX model fails to load or initialize.
+    """
+
+    def __init__(
+        self,
+        *,
+        model_name: YOLOv5FaceWeights = YOLOv5FaceWeights.YOLOV5S,
+        conf_thresh: float = 0.6,
+        nms_thresh: float = 0.5,
+        input_size: int = 640,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            conf_thresh=conf_thresh,
+            nms_thresh=nms_thresh,
+            input_size=input_size,
+            **kwargs,
+        )
+        self._supports_landmarks = True  # YOLOv5-Face supports landmarks
+
+        # Validate input size
+        if input_size != 640:
+            raise ValueError(
+                f'YOLOv5Face only supports input_size=640 (got {input_size}). The ONNX model has a fixed input shape.'
+            )
+
+        self.model_name = model_name
+        self.conf_thresh = conf_thresh
+        self.nms_thresh = nms_thresh
+        self.input_size = input_size
+
+        # Advanced options from kwargs
+        self.max_det = kwargs.get('max_det', 750)
+
+        Logger.info(
+            f'Initializing YOLOv5Face with model={self.model_name}, conf_thresh={self.conf_thresh}, '
+            f'nms_thresh={self.nms_thresh}, input_size={self.input_size}'
+        )
+
+        # Get path to model weights
+        self._model_path = verify_model_weights(self.model_name)
+        Logger.info(f'Verified model weights located at: {self._model_path}')
+
+        # Initialize model
+        self._initialize_model(self._model_path)
+
+    def _initialize_model(self, model_path: str) -> None:
+        """
+        Initializes an ONNX model session from the given path.
+
+        Args:
+            model_path (str): The file path to the ONNX model.
+
+        Raises:
+            RuntimeError: If the model fails to load, logs an error and raises an exception.
+        """
+        try:
+            self.session = create_onnx_session(model_path)
+            self.input_names = self.session.get_inputs()[0].name
+            self.output_names = [x.name for x in self.session.get_outputs()]
+            Logger.info(f'Successfully initialized the model from {model_path}')
+        except Exception as e:
+            Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
+            raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
+
+    def preprocess(self, image: np.ndarray) -> Tuple[np.ndarray, float, Tuple[int, int]]:
+        """
+        Preprocess image for inference.
+
+        Args:
+            image (np.ndarray): Input image (BGR format)
+
+        Returns:
+            Tuple[np.ndarray, float, Tuple[int, int]]: Preprocessed image, scale ratio, and padding
+        """
+        # Get original image shape
+        img_h, img_w = image.shape[:2]
+
+        # Calculate scale ratio
+        scale = min(self.input_size / img_h, self.input_size / img_w)
+        new_h, new_w = int(img_h * scale), int(img_w * scale)
+
+        # Resize image
+        img_resized = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_LINEAR)
+
+        # Create padded image
+        img_padded = np.full((self.input_size, self.input_size, 3), 114, dtype=np.uint8)
+
+        # Calculate padding
+        pad_h = (self.input_size - new_h) // 2
+        pad_w = (self.input_size - new_w) // 2
+
+        # Place resized image in center
+        img_padded[pad_h : pad_h + new_h, pad_w : pad_w + new_w] = img_resized
+
+        # Convert to RGB and normalize
+        img_rgb = cv2.cvtColor(img_padded, cv2.COLOR_BGR2RGB)
+        img_normalized = img_rgb.astype(np.float32) / 255.0
+
+        # Transpose to CHW format (HWC -> CHW) and add batch dimension
+        img_transposed = np.transpose(img_normalized, (2, 0, 1))
+        img_batch = np.expand_dims(img_transposed, axis=0)
+        img_batch = np.ascontiguousarray(img_batch)
+
+        return img_batch, scale, (pad_w, pad_h)
+
+    def inference(self, input_tensor: np.ndarray) -> List[np.ndarray]:
+        """Perform model inference on the preprocessed image tensor.
+
+        Args:
+            input_tensor (np.ndarray): Preprocessed input tensor.
+
+        Returns:
+            List[np.ndarray]: Raw model outputs.
+        """
+        return self.session.run(self.output_names, {self.input_names: input_tensor})
+
+    def postprocess(
+        self,
+        predictions: np.ndarray,
+        scale: float,
+        padding: Tuple[int, int],
+    ) -> Tuple[np.ndarray, np.ndarray]:
+        """
+        Postprocess model predictions.
+
+        Args:
+            predictions (np.ndarray): Raw model output
+            scale (float): Scale ratio used in preprocessing
+            padding (Tuple[int, int]): Padding used in preprocessing
+
+        Returns:
+            Tuple[np.ndarray, np.ndarray]: Filtered detections and landmarks
+                - detections: [x1, y1, x2, y2, conf]
+                - landmarks: [5, 2] for each detection
+        """
+        # predictions shape: (1, 25200, 16)
+        # 16 = [x, y, w, h, obj_conf, cls_conf, 10 landmarks (5 points * 2 coords)]
+
+        predictions = predictions[0]  # Remove batch dimension
+
+        # Filter by confidence
+        mask = predictions[:, 4] >= self.conf_thresh
+        predictions = predictions[mask]
+
+        if len(predictions) == 0:
+            return np.array([]), np.array([])
+
+        # Convert from xywh to xyxy
+        boxes = self._xywh2xyxy(predictions[:, :4])
+
+        # Get confidence scores
+        scores = predictions[:, 4]
+
+        # Get landmarks (5 points, 10 coordinates)
+        landmarks = predictions[:, 5:15].copy()
+
+        # Apply NMS
+        detections_for_nms = np.hstack((boxes, scores[:, None])).astype(np.float32, copy=False)
+        keep = non_max_suppression(detections_for_nms, self.nms_thresh)
+
+        if len(keep) == 0:
+            return np.array([]), np.array([])
+
+        # Filter detections and limit to max_det
+        keep = keep[: self.max_det]
+        boxes = boxes[keep]
+        scores = scores[keep]
+        landmarks = landmarks[keep]
+
+        # Scale back to original image coordinates
+        pad_w, pad_h = padding
+        boxes[:, [0, 2]] = (boxes[:, [0, 2]] - pad_w) / scale
+        boxes[:, [1, 3]] = (boxes[:, [1, 3]] - pad_h) / scale
+
+        # Scale landmarks
+        for i in range(5):
+            landmarks[:, i * 2] = (landmarks[:, i * 2] - pad_w) / scale
+            landmarks[:, i * 2 + 1] = (landmarks[:, i * 2 + 1] - pad_h) / scale
+
+        # Reshape landmarks to (N, 5, 2)
+        landmarks = landmarks.reshape(-1, 5, 2)
+
+        # Combine results
+        detections = np.concatenate([boxes, scores[:, None]], axis=1)
+
+        return detections, landmarks
+
+    def _xywh2xyxy(self, x: np.ndarray) -> np.ndarray:
+        """
+        Convert bounding box format from xywh to xyxy.
+
+        Args:
+            x (np.ndarray): Boxes in [x, y, w, h] format
+
+        Returns:
+            np.ndarray: Boxes in [x1, y1, x2, y2] format
+        """
+        y = np.copy(x)
+        y[..., 0] = x[..., 0] - x[..., 2] / 2  # x1
+        y[..., 1] = x[..., 1] - x[..., 3] / 2  # y1
+        y[..., 2] = x[..., 0] + x[..., 2] / 2  # x2
+        y[..., 3] = x[..., 1] + x[..., 3] / 2  # y2
+        return y
+
+    def detect(
+        self,
+        image: np.ndarray,
+        *,
+        max_num: int = 0,
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
+    ) -> List[Dict[str, Any]]:
+        """
+        Perform face detection on an input image and return bounding boxes and facial landmarks.
+
+        Args:
+            image (np.ndarray): Input image as a NumPy array of shape (H, W, C).
+            max_num (int): Maximum number of detections to return. Use 0 to return all detections. Defaults to 0.
+            metric (Literal["default", "max"]): Metric for ranking detections when `max_num` is limited.
+                - "default": Prioritize detections closer to the image center.
+                - "max": Prioritize detections with larger bounding box areas.
+            center_weight (float): Weight for penalizing detections farther from the image center
+                when using the "default" metric. Defaults to 2.0.
+
+        Returns:
+            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
+                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
+                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
+            ...     confidence = face['confidence']  # float
+            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
+        """
+
+        original_height, original_width = image.shape[:2]
+
+        # Preprocess
+        image_tensor, scale, padding = self.preprocess(image)
+
+        # ONNXRuntime inference
+        outputs = self.inference(image_tensor)
+
+        # Postprocess
+        detections, landmarks = self.postprocess(outputs[0], scale, padding)
+
+        # Handle case when no faces are detected
+        if len(detections) == 0:
+            return []
+
+        if 0 < max_num < detections.shape[0]:
+            # Calculate area of detections
+            area = (detections[:, 2] - detections[:, 0]) * (detections[:, 3] - detections[:, 1])
+
+            # Calculate offsets from image center
+            center = (original_height // 2, original_width // 2)
+            offsets = np.vstack(
+                [
+                    (detections[:, 0] + detections[:, 2]) / 2 - center[1],
+                    (detections[:, 1] + detections[:, 3]) / 2 - center[0],
+                ]
+            )
+
+            # Calculate scores based on the chosen metric
+            offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
+            if metric == 'max':
+                values = area
+            else:
+                values = area - offset_dist_squared * center_weight
+
+            # Sort by scores and select top `max_num`
+            sorted_indices = np.argsort(values)[::-1][:max_num]
+            detections = detections[sorted_indices]
+            landmarks = landmarks[sorted_indices]
+
+        faces = []
+        for i in range(detections.shape[0]):
+            face_dict = {
+                'bbox': detections[i, :4],
+                'confidence': float(detections[i, 4]),
+                'landmarks': landmarks[i],
+            }
+            faces.append(face_dict)
+
+        return faces

uniface/face.py

@@ -0,0 +1,66 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from dataclasses import asdict, dataclass
+from typing import Optional
+
+import numpy as np
+
+from uniface.face_utils import compute_similarity
+
+__all__ = ['Face']
+
+
+@dataclass
+class Face:
+    """
+    Detected face with analysis results.
+    """
+
+    # Required attributes
+    bbox: np.ndarray
+    confidence: float
+    landmarks: np.ndarray
+
+    # Optional attributes
+    embedding: Optional[np.ndarray] = None
+    age: Optional[int] = None
+    gender: Optional[int] = None  # 0 or 1
+
+    def compute_similarity(self, other: 'Face') -> float:
+        """Compute cosine similarity with another face."""
+        if self.embedding is None or other.embedding is None:
+            raise ValueError('Both faces must have embeddings for similarity computation')
+        return float(compute_similarity(self.embedding, other.embedding))
+
+    def to_dict(self) -> dict:
+        """Convert to dictionary."""
+        return asdict(self)
+
+    @property
+    def sex(self) -> str:
+        """Get gender as a string label (Female or Male)."""
+        if self.gender is None:
+            return None
+        return 'Female' if self.gender == 0 else 'Male'
+
+    @property
+    def bbox_xyxy(self) -> np.ndarray:
+        """Get bounding box coordinates in (x1, y1, x2, y2) format."""
+        return self.bbox.copy()
+
+    @property
+    def bbox_xywh(self) -> np.ndarray:
+        """Get bounding box coordinates in (x1, y1, w, h) format."""
+        return np.array([self.bbox[0], self.bbox[1], self.bbox[2] - self.bbox[0], self.bbox[3] - self.bbox[1]])
+
+    def __repr__(self) -> str:
+        parts = [f'Face(confidence={self.confidence:.3f}']
+        if self.age is not None:
+            parts.append(f'age={self.age}')
+        if self.gender is not None:
+            parts.append(f'sex={self.sex}')
+        if self.embedding is not None:
+            parts.append(f'embedding_dim={self.embedding.shape[0]}')
+        return ', '.join(parts) + ')'

uniface/face_utils.py

@@ -2,13 +2,18 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from typing import Tuple, Union
+
 import cv2
 import numpy as np
 from skimage.transform import SimilarityTransform
-from typing import Tuple
 
-
-__all__ = ["face_alignment", "compute_similarity", "bbox_center_alignment", "transform_points_2d"]
+__all__ = [
+    'face_alignment',
+    'compute_similarity',
+    'bbox_center_alignment',
+    'transform_points_2d',
+]
 
 
 # Reference alignment for facial landmarks (ArcFace)
@@ -18,19 +23,20 @@ reference_alignment: np.ndarray = np.array(
         [73.5318, 51.5014],
         [56.0252, 71.7366],
         [41.5493, 92.3655],
-        [70.7299, 92.2041]
+        [70.7299, 92.2041],
     ],
-    dtype=np.float32
+    dtype=np.float32,
 )
 
 
-def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarray, np.ndarray]:
+def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]] = 112) -> Tuple[np.ndarray, np.ndarray]:
     """
     Estimate the normalization transformation matrix for facial landmarks.
 
     Args:
         landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (int, optional): The size of the output image. Default is 112.
+        image_size (Union[int, Tuple[int, int]], optional): The size of the output image.
+            Can be an integer (for square images) or a tuple (width, height). Default is 112.
 
     Returns:
         np.ndarray: The 2x3 transformation matrix for aligning the landmarks.
@@ -40,14 +46,21 @@ def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarr
         AssertionError: If the input landmark array does not have the shape (5, 2)
                         or if image_size is not a multiple of 112 or 128.
     """
-    assert landmark.shape == (5, 2), "Landmark array must have shape (5, 2)."
-    assert image_size % 112 == 0 or image_size % 128 == 0, "Image size must be a multiple of 112 or 128."
+    assert landmark.shape == (5, 2), 'Landmark array must have shape (5, 2).'
 
-    if image_size % 112 == 0:
-        ratio = float(image_size) / 112.0
+    # Handle both int and tuple inputs
+    if isinstance(image_size, tuple):
+        size = image_size[0]  # Use width for ratio calculation
+    else:
+        size = image_size
+
+    assert size % 112 == 0 or size % 128 == 0, 'Image size must be a multiple of 112 or 128.'
+
+    if size % 112 == 0:
+        ratio = float(size) / 112.0
         diff_x = 0.0
     else:
-        ratio = float(image_size) / 128.0
+        ratio = float(size) / 128.0
         diff_x = 8.0 * ratio
 
     # Adjust reference alignment based on ratio and diff_x
@@ -64,14 +77,19 @@ def estimate_norm(landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarr
     return matrix, inverse_matrix
 
 
-def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: int = 112) -> Tuple[np.ndarray, np.ndarray]:
+def face_alignment(
+    image: np.ndarray,
+    landmark: np.ndarray,
+    image_size: Union[int, Tuple[int, int]] = 112,
+) -> Tuple[np.ndarray, np.ndarray]:
     """
     Align the face in the input image based on the given facial landmarks.
 
     Args:
         image (np.ndarray): Input image as a NumPy array.
         landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (int, optional): The size of the aligned output image. Default is 112.
+        image_size (Union[int, Tuple[int, int]], optional): The size of the aligned output image.
+            Can be an integer (for square images) or a tuple (width, height). Default is 112.
 
     Returns:
         np.ndarray: The aligned face as a NumPy array.
@@ -80,8 +98,14 @@ def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: int = 11
     # Get the transformation matrix
     M, M_inv = estimate_norm(landmark, image_size)
 
+    # Handle both int and tuple for warpAffine output size
+    if isinstance(image_size, int):
+        output_size = (image_size, image_size)
+    else:
+        output_size = image_size
+
     # Warp the input image to align the face
-    warped = cv2.warpAffine(image, M, (image_size, image_size), borderValue=0.0)
+    warped = cv2.warpAffine(image, M, output_size, borderValue=0.0)
 
     return warped, M_inv
 

uniface/landmark/__init__.py

@@ -2,8 +2,8 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from .models import Landmark106
 from .base import BaseLandmarker
+from .models import Landmark106
 
 
 def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
@@ -25,8 +25,4 @@ def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
 
-__all__ = [
-    "create_landmarker",
-    "Landmark106",
-    "BaseLandmarker"
-]
+__all__ = ['create_landmarker', 'Landmark106', 'BaseLandmarker']

uniface/landmark/base.py

@@ -3,6 +3,7 @@
 # GitHub: https://github.com/yakhyo
 
 from abc import ABC, abstractmethod
+
 import numpy as np
 
 
@@ -10,6 +11,7 @@ class BaseLandmarker(ABC):
     """
     Abstract Base Class for all facial landmark models.
     """
+
     @abstractmethod
     def get_landmarks(self, image: np.ndarray, bbox: np.ndarray) -> np.ndarray:
         """

uniface/landmark/models.py

@@ -2,18 +2,20 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import cv2
-import numpy as np
 from typing import Tuple
 
-from uniface.log import Logger
+import cv2
+import numpy as np
+
 from uniface.constants import LandmarkWeights
-from uniface.model_store import verify_model_weights
 from uniface.face_utils import bbox_center_alignment, transform_points_2d
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
+
 from .base import BaseLandmarker
 
-__all__ = ['Landmark']
+__all__ = ['Landmark106']
 
 
 class Landmark106(BaseLandmarker):
@@ -40,15 +42,13 @@ class Landmark106(BaseLandmarker):
         >>> print(landmarks.shape)
         (106, 2)
     """
+
     def __init__(
         self,
         model_name: LandmarkWeights = LandmarkWeights.DEFAULT,
-        input_size: Tuple[int, int] = (192, 192)
+        input_size: Tuple[int, int] = (192, 192),
     ) -> None:
-        Logger.info(
-            f"Initializing Facial Landmark with model={model_name}, "
-            f"input_size={input_size}"
-        )
+        Logger.info(f'Initializing Facial Landmark with model={model_name}, input_size={input_size}')
         self.input_size = input_size
         self.input_std = 1.0
         self.input_mean = 0.0
@@ -79,11 +79,11 @@ class Landmark106(BaseLandmarker):
             self.lmk_dim = 2  # x,y coordinates
             self.lmk_num = output_shape[1] // self.lmk_dim  # Number of landmarks
 
-            Logger.info(f"Model initialized with {self.lmk_num} landmarks")
+            Logger.info(f'Model initialized with {self.lmk_num} landmarks')
 
         except Exception as e:
             Logger.error(f"Failed to load landmark model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize landmark model: {e}")
+            raise RuntimeError(f'Failed to initialize landmark model: {e}') from e
 
     def preprocess(self, image: np.ndarray, bbox: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
         """Prepares a face crop for inference.
@@ -108,8 +108,11 @@ class Landmark106(BaseLandmarker):
         aligned_face, transform_matrix = bbox_center_alignment(image, center, self.input_size[0], scale, 0.0)
 
         face_blob = cv2.dnn.blobFromImage(
-            aligned_face, 1.0 / self.input_std, self.input_size,
-            (self.input_mean, self.input_mean, self.input_mean), swapRB=True
+            aligned_face,
+            1.0 / self.input_std,
+            self.input_size,
+            (self.input_mean, self.input_mean, self.input_mean),
+            swapRB=True,
         )
         return face_blob, transform_matrix
 
@@ -129,7 +132,7 @@ class Landmark106(BaseLandmarker):
         """
         landmarks = predictions.reshape((-1, 2))
         landmarks[:, 0:2] += 1
-        landmarks[:, 0:2] *= (self.input_size[0] // 2)
+        landmarks[:, 0:2] *= self.input_size[0] // 2
 
         inverse_matrix = cv2.invertAffineTransform(transform_matrix)
         landmarks = transform_points_2d(landmarks, inverse_matrix)
@@ -149,27 +152,22 @@ class Landmark106(BaseLandmarker):
             np.ndarray: An array of predicted landmark points with shape (106, 2).
         """
         face_blob, transform_matrix = self.preprocess(image, bbox)
-        raw_predictions = self.session.run(
-            self.output_names, {self.input_names[0]: face_blob}
-        )[0][0]
+        raw_predictions = self.session.run(self.output_names, {self.input_names[0]: face_blob})[0][0]
         landmarks = self.postprocess(raw_predictions, transform_matrix)
         return landmarks
 
 
+# Testing code
+if __name__ == '__main__':
+    from uniface.detection import RetinaFace
+    from uniface.landmark import Landmark106
 
-# TODO: For testing purposes only, remote later
-if __name__ == "__main__":
-    # UPDATED: Use the high-level factory functions
-    from uniface.detection import create_detector
-    from uniface.landmark import create_landmarker
-
-    # 1. Create the detector and landmarker using the new API
-    face_detector = create_detector('retinaface')
-    landmarker = create_landmarker() # Uses the default '2d106det' method
+    face_detector = RetinaFace()
+    landmarker = Landmark106()
 
     cap = cv2.VideoCapture(0)
     if not cap.isOpened():
-        print("Webcam not available.")
+        print('Webcam not available.')
         exit()
 
     print("Press 'q' to quit.")
@@ -177,14 +175,14 @@ if __name__ == "__main__":
     while True:
         ret, frame = cap.read()
         if not ret:
-            print("Frame capture failed.")
+            print('Frame capture failed.')
             break
 
         # 2. The detect method returns a list of dictionaries
         faces = face_detector.detect(frame)
 
         if not faces:
-            cv2.imshow("Facial Landmark Detection", frame)
+            cv2.imshow('Facial Landmark Detection', frame)
             if cv2.waitKey(1) & 0xFF == ord('q'):
                 break
             continue
@@ -199,14 +197,14 @@ if __name__ == "__main__":
 
             # --- Drawing Logic ---
             # Draw the landmarks
-            for (x, y) in landmarks.astype(int):
+            for x, y in landmarks.astype(int):
                 cv2.circle(frame, (x, y), 2, (0, 255, 0), -1)
 
             # Draw the bounding box
             x1, y1, x2, y2 = map(int, bbox)
             cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
 
-        cv2.imshow("Facial Landmark Detection", frame)
+        cv2.imshow('Facial Landmark Detection', frame)
         if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 

uniface/log.py

@@ -1,7 +1,7 @@
 import logging
 
 # Create logger for uniface
-Logger = logging.getLogger("uniface")
+Logger = logging.getLogger('uniface')
 Logger.setLevel(logging.WARNING)  # Only show warnings/errors by default
 Logger.addHandler(logging.NullHandler())
 
@@ -19,10 +19,7 @@ def enable_logging(level=logging.INFO):
     """
     Logger.handlers.clear()
     handler = logging.StreamHandler()
-    handler.setFormatter(logging.Formatter(
-        "%(asctime)s - %(levelname)s - %(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S"
-    ))
+    handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s', datefmt='%Y-%m-%d %H:%M:%S'))
     Logger.addHandler(handler)
     Logger.setLevel(level)
     Logger.propagate = False

uniface/model_store.py

@@ -2,14 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import os
 import hashlib
+import os
+
 import requests
 from tqdm import tqdm
 
-from uniface.log import Logger
 import uniface.constants as const
-
+from uniface.log import Logger
 
 __all__ = ['verify_model_weights']
 
@@ -62,12 +62,12 @@ def verify_model_weights(model_name: str, root: str = '~/.uniface/models') -> st
             Logger.info(f"Successfully downloaded '{model_name}' to {model_path}")
         except Exception as e:
             Logger.error(f"Failed to download model '{model_name}': {e}")
-            raise ConnectionError(f"Download failed for '{model_name}'")
+            raise ConnectionError(f"Download failed for '{model_name}'") from e
 
     expected_hash = const.MODEL_SHA256.get(model_name)
     if expected_hash and not verify_file_hash(model_path, expected_hash):
         os.remove(model_path)  # Remove corrupted file
-        Logger.warning("Corrupted weight detected. Removing...")
+        Logger.warning('Corrupted weight detected. Removing...')
         raise ValueError(f"Hash mismatch for '{model_name}'. The file may be corrupted; please try downloading again.")
 
     return model_path
@@ -78,33 +78,36 @@ def download_file(url: str, dest_path: str) -> None:
     try:
         response = requests.get(url, stream=True)
         response.raise_for_status()
-        with open(dest_path, "wb") as file, tqdm(
-            desc=f"Downloading {dest_path}",
-            unit='B',
-            unit_scale=True,
-            unit_divisor=1024
-        ) as progress:
+        with (
+            open(dest_path, 'wb') as file,
+            tqdm(
+                desc=f'Downloading {dest_path}',
+                unit='B',
+                unit_scale=True,
+                unit_divisor=1024,
+            ) as progress,
+        ):
             for chunk in response.iter_content(chunk_size=const.CHUNK_SIZE):
                 if chunk:
                     file.write(chunk)
                     progress.update(len(chunk))
     except requests.RequestException as e:
-        raise ConnectionError(f"Failed to download file from {url}. Error: {e}")
+        raise ConnectionError(f'Failed to download file from {url}. Error: {e}') from e
 
 
 def verify_file_hash(file_path: str, expected_hash: str) -> bool:
     """Compute the SHA-256 hash of the file and compare it with the expected hash."""
     file_hash = hashlib.sha256()
-    with open(file_path, "rb") as f:
-        for chunk in iter(lambda: f.read(const.CHUNK_SIZE), b""):
+    with open(file_path, 'rb') as f:
+        for chunk in iter(lambda: f.read(const.CHUNK_SIZE), b''):
             file_hash.update(chunk)
     actual_hash = file_hash.hexdigest()
     if actual_hash != expected_hash:
-        Logger.warning(f"Expected hash: {expected_hash}, but got: {actual_hash}")
+        Logger.warning(f'Expected hash: {expected_hash}, but got: {actual_hash}')
     return actual_hash == expected_hash
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     model_names = [model.value for model in const.RetinaFaceWeights]
 
     # Download each model in the list

uniface/onnx_utils.py

@@ -2,10 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""
-Utilities for ONNX Runtime configuration and provider selection.
-"""
-
 from typing import List
 
 import onnxruntime as ort
@@ -35,19 +31,19 @@ def get_available_providers() -> List[str]:
     providers = []
 
     # Priority order: CoreML > CUDA > CPU
-    if "CoreMLExecutionProvider" in available:
-        providers.append("CoreMLExecutionProvider")
-        Logger.info("CoreML acceleration enabled (Apple Silicon)")
+    if 'CoreMLExecutionProvider' in available:
+        providers.append('CoreMLExecutionProvider')
+        Logger.info('CoreML acceleration enabled (Apple Silicon)')
 
-    if "CUDAExecutionProvider" in available:
-        providers.append("CUDAExecutionProvider")
-        Logger.info("CUDA acceleration enabled (NVIDIA GPU)")
+    if 'CUDAExecutionProvider' in available:
+        providers.append('CUDAExecutionProvider')
+        Logger.info('CUDA acceleration enabled (NVIDIA GPU)')
 
     # CPU is always available as fallback
-    providers.append("CPUExecutionProvider")
+    providers.append('CPUExecutionProvider')
 
     if len(providers) == 1:
-        Logger.info("Using CPU execution (no hardware acceleration detected)")
+        Logger.info('Using CPU execution (no hardware acceleration detected)')
 
     return providers
 
@@ -77,11 +73,27 @@ def create_onnx_session(model_path: str, providers: List[str] = None) -> ort.Inf
     if providers is None:
         providers = get_available_providers()
 
+    # Suppress ONNX Runtime warnings (e.g., CoreML partition warnings)
+    # Log levels: 0=VERBOSE, 1=INFO, 2=WARNING, 3=ERROR, 4=FATAL
+    sess_options = ort.SessionOptions()
+    sess_options.log_severity_level = 3  # Only show ERROR and FATAL
+
     try:
-        session = ort.InferenceSession(model_path, providers=providers)
+        session = ort.InferenceSession(model_path, sess_options=sess_options, providers=providers)
         active_provider = session.get_providers()[0]
-        Logger.debug(f"Session created with provider: {active_provider}")
+        Logger.debug(f'Session created with provider: {active_provider}')
+
+        # Show user-friendly message about which provider is being used
+        provider_names = {
+            'CoreMLExecutionProvider': 'CoreML (Apple Silicon)',
+            'CUDAExecutionProvider': 'CUDA (NVIDIA GPU)',
+            'CPUExecutionProvider': 'CPU',
+        }
+        provider_display = provider_names.get(active_provider, active_provider)
+        Logger.debug(f'Model loaded with provider: {active_provider}')
+        print(f'✓ Model loaded ({provider_display})')
+
         return session
     except Exception as e:
-        Logger.error(f"Failed to create ONNX session: {e}", exc_info=True)
-        raise RuntimeError(f"Failed to initialize ONNX Runtime session: {e}") from e
+        Logger.error(f'Failed to create ONNX session: {e}', exc_info=True)
+        raise RuntimeError(f'Failed to initialize ONNX Runtime session: {e}') from e

uniface/recognition/__init__.py

@@ -2,10 +2,10 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Dict
-from .models import ArcFace, MobileFace, SphereFace
+
 from .base import BaseRecognizer
-from uniface.constants import ArcFaceWeights, MobileFaceWeights, SphereFaceWeights
+from .models import ArcFace, MobileFace, SphereFace
+
 
 def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
     """
@@ -54,10 +54,11 @@ def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
         available = ['arcface', 'mobileface', 'sphereface']
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
+
 __all__ = [
-    "create_recognizer",
-    "ArcFace",
-    "MobileFace",
-    "SphereFace",
-    "BaseRecognizer",
-]
+    'create_recognizer',
+    'ArcFace',
+    'MobileFace',
+    'SphereFace',
+    'BaseRecognizer',
+]

uniface/recognition/base.py

@@ -3,13 +3,14 @@
 # GitHub: https://github.com/yakhyo
 
 from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import List, Tuple, Union
+
 import cv2
 import numpy as np
-from dataclasses import dataclass
-from typing import Tuple, Union, List
 
-from uniface.log import Logger
 from uniface.face_utils import face_alignment
+from uniface.log import Logger
 from uniface.onnx_utils import create_onnx_session
 
 
@@ -18,6 +19,7 @@ class PreprocessConfig:
     """
     Configuration for preprocessing images before feeding them into the model.
     """
+
     input_mean: Union[float, List[float]] = 127.5
     input_std: Union[float, List[float]] = 127.5
     input_size: Tuple[int, int] = (112, 112)
@@ -28,6 +30,7 @@ class BaseRecognizer(ABC):
     Abstract Base Class for all face recognition models.
     It provides the core functionality for preprocessing, inference, and embedding extraction.
     """
+
     @abstractmethod
     def __init__(self, model_path: str, preprocessing: PreprocessConfig) -> None:
         """
@@ -63,17 +66,20 @@ class BaseRecognizer(ABC):
             input_shape = input_cfg.shape
             model_input_size = tuple(input_shape[2:4][::-1])  # (width, height)
             if model_input_size != self.input_size:
-                Logger.warning(f"Model input size {model_input_size} differs from configured size {self.input_size}")
+                Logger.warning(f'Model input size {model_input_size} differs from configured size {self.input_size}')
 
             # Extract output configuration
             self.output_names = [output.name for output in self.session.get_outputs()]
             self.output_shape = self.session.get_outputs()[0].shape
 
-            assert len(self.output_names) == 1, "Expected only one output node."
-            Logger.info(f"Successfully initialized face encoder from {self.model_path}")
+            assert len(self.output_names) == 1, 'Expected only one output node.'
+            Logger.info(f'Successfully initialized face encoder from {self.model_path}')
 
         except Exception as e:
-            Logger.error(f"Failed to load face encoder model from '{self.model_path}'", exc_info=True)
+            Logger.error(
+                f"Failed to load face encoder model from '{self.model_path}'",
+                exc_info=True,
+            )
             raise RuntimeError(f"Failed to initialize model session for '{self.model_path}'") from e
 
     def preprocess(self, face_img: np.ndarray) -> np.ndarray:
@@ -91,8 +97,9 @@ class BaseRecognizer(ABC):
         if isinstance(self.input_std, (list, tuple)):
             # Per-channel normalization
             rgb_img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2RGB).astype(np.float32)
-            normalized_img = (rgb_img - np.array(self.input_mean, dtype=np.float32)) / \
-                np.array(self.input_std, dtype=np.float32)
+            normalized_img = (rgb_img - np.array(self.input_mean, dtype=np.float32)) / np.array(
+                self.input_std, dtype=np.float32
+            )
 
             # Change to NCHW (batch, channels, height, width)
             blob = np.transpose(normalized_img, (2, 0, 1))  # CHW
@@ -104,24 +111,28 @@ class BaseRecognizer(ABC):
                 scalefactor=1.0 / self.input_std,
                 size=self.input_size,
                 mean=(self.input_mean, self.input_mean, self.input_mean),
-                swapRB=True  # Convert BGR to RGB
+                swapRB=True,  # Convert BGR to RGB
             )
 
         return blob
 
-    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray) -> np.ndarray:
+    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray = None) -> np.ndarray:
         """
         Extracts face embedding from an image.
 
         Args:
-            image: Input face image (BGR format).
-            landmarks: Facial landmarks (5 points for alignment).
+            image: Input face image (BGR format). If already aligned (112x112), landmarks can be None.
+            landmarks: Facial landmarks (5 points for alignment). Optional if image is already aligned.
 
         Returns:
             Face embedding vector (typically 512-dimensional).
         """
-        # Align face using landmarks
-        aligned_face, _ = face_alignment(image, landmarks)
+        # If landmarks are provided, align the face first
+        if landmarks is not None:
+            aligned_face, _ = face_alignment(image, landmarks, image_size=self.input_size)
+        else:
+            # Assume image is already aligned
+            aligned_face = image
 
         # Generate embedding from aligned face
         face_blob = self.preprocess(aligned_face)

uniface/recognition/models.py

@@ -6,9 +6,10 @@ from typing import Optional
 
 from uniface.constants import ArcFaceWeights, MobileFaceWeights, SphereFaceWeights
 from uniface.model_store import verify_model_weights
+
 from .base import BaseRecognizer, PreprocessConfig
 
-__all__ = ["ArcFace", "MobileFace", "SphereFace"]
+__all__ = ['ArcFace', 'MobileFace', 'SphereFace']
 
 
 class ArcFace(BaseRecognizer):
@@ -33,14 +34,10 @@ class ArcFace(BaseRecognizer):
     def __init__(
         self,
         model_name: ArcFaceWeights = ArcFaceWeights.MNET,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: Optional[PreprocessConfig] = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)
 
@@ -67,14 +64,10 @@ class MobileFace(BaseRecognizer):
     def __init__(
         self,
         model_name: MobileFaceWeights = MobileFaceWeights.MNET_V2,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: Optional[PreprocessConfig] = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)
 
@@ -101,14 +94,10 @@ class SphereFace(BaseRecognizer):
     def __init__(
         self,
         model_name: SphereFaceWeights = SphereFaceWeights.SPHERE20,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: Optional[PreprocessConfig] = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
 
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)

uniface/visualization.py

@@ -2,49 +2,127 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from typing import List, Tuple, Union
+
 import cv2
 import numpy as np
-from typing import List, Union
 
 
 def draw_detections(
+    *,
     image: np.ndarray,
-    bboxes: Union[np.ndarray, List[List[float]]],
+    bboxes: Union[List[np.ndarray], List[List[float]]],
     scores: Union[np.ndarray, List[float]],
-    landmarks: Union[np.ndarray, List[List[List[float]]]],
-    vis_threshold: float = 0.6
+    landmarks: Union[List[np.ndarray], List[List[List[float]]]],
+    vis_threshold: float = 0.6,
+    draw_score: bool = False,
+    fancy_bbox: bool = True,
 ):
     """
-    Draws bounding boxes, scores, and landmarks from separate lists onto an image.
+    Draws bounding boxes, landmarks, and optional scores on an image.
 
     Args:
-        image (np.ndarray): The image to draw on.
-        bboxes (list or np.ndarray): A list of bounding boxes, e.g., [[x1,y1,x2,y2], ...].
-        scores (list or np.ndarray): A list of confidence scores.
-        landmarks (list or np.ndarray): A list of landmark sets, e.g., [[[x,y],...],...].
-        vis_threshold (float): Confidence threshold for filtering which detections to draw.
+        image: Input image to draw on.
+        bboxes: List of bounding boxes [x1, y1, x2, y2].
+        scores: List of confidence scores.
+        landmarks: List of landmark sets with shape (5, 2).
+        vis_threshold: Confidence threshold for filtering. Defaults to 0.6.
+        draw_score: Whether to draw confidence scores. Defaults to False.
     """
-    _colors = [(0, 0, 255), (0, 255, 255), (255, 0, 255), (0, 255, 0), (255, 0, 0)]
+    colors = [(0, 0, 255), (0, 255, 255), (255, 0, 255), (0, 255, 0), (255, 0, 0)]
 
-    # Filter detections by score
+    # Calculate line thickness based on image size
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    # Filter detections by confidence threshold
     keep_indices = [i for i, score in enumerate(scores) if score >= vis_threshold]
 
-    # Draw the filtered detections
     for i in keep_indices:
         bbox = np.array(bboxes[i], dtype=np.int32)
         score = scores[i]
         landmark_set = np.array(landmarks[i], dtype=np.int32)
 
-        # Calculate adaptive thickness
-        thickness = max(1, int(min(bbox[2] - bbox[0], bbox[3] - bbox[1]) / 100))
+        # Calculate dynamic font scale based on bbox height
+        bbox_h = bbox[3] - bbox[1]
+        font_scale = max(0.4, min(0.7, bbox_h / 200))
+        font_thickness = 2
 
         # Draw bounding box
-        cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 0, 255), thickness)
+        if fancy_bbox:
+            draw_fancy_bbox(image, bbox, color=(0, 255, 0), thickness=line_thickness, proportion=0.2)
+        else:
+            cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 255, 0), line_thickness)
 
-        # Draw score
-        cv2.putText(image, f"{score:.2f}", (bbox[0], bbox[1] - 10),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), thickness)
+        # Draw confidence score with background
+        if draw_score:
+            text = f'{score:.2f}'
+            (text_width, text_height), baseline = cv2.getTextSize(
+                text, cv2.FONT_HERSHEY_SIMPLEX, font_scale, font_thickness
+            )
+
+            # Draw background rectangle
+            cv2.rectangle(
+                image,
+                (bbox[0], bbox[1] - text_height - baseline - 10),
+                (bbox[0] + text_width + 10, bbox[1]),
+                (0, 255, 0),
+                -1,
+            )
+
+            # Draw text
+            cv2.putText(
+                image,
+                text,
+                (bbox[0] + 5, bbox[1] - 5),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                font_scale,
+                (0, 0, 0),
+                font_thickness,
+            )
 
         # Draw landmarks
         for j, point in enumerate(landmark_set):
-            cv2.circle(image, tuple(point), thickness + 1, _colors[j], -1)
+            cv2.circle(image, tuple(point), line_thickness + 1, colors[j], -1)
+
+
+def draw_fancy_bbox(
+    image: np.ndarray,
+    bbox: np.ndarray,
+    color: Tuple[int, int, int] = (0, 255, 0),
+    thickness: int = 3,
+    proportion: float = 0.2,
+):
+    """
+    Draws a bounding box with fancy corners on an image.
+
+    Args:
+        image: Input image to draw on.
+        bbox: Bounding box coordinates [x1, y1, x2, y2].
+        color: Color of the bounding box. Defaults to green.
+        thickness: Thickness of the bounding box lines. Defaults to 3.
+        proportion: Proportion of the corner length to the width/height of the bounding box. Defaults to 0.2.
+    """
+    x1, y1, x2, y2 = map(int, bbox)
+    width = x2 - x1
+    height = y2 - y1
+
+    corner_length = int(proportion * min(width, height))
+
+    # Draw the rectangle
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, 1)
+
+    # Top-left corner
+    cv2.line(image, (x1, y1), (x1 + corner_length, y1), color, thickness)
+    cv2.line(image, (x1, y1), (x1, y1 + corner_length), color, thickness)
+
+    # Top-right corner
+    cv2.line(image, (x2, y1), (x2 - corner_length, y1), color, thickness)
+    cv2.line(image, (x2, y1), (x2, y1 + corner_length), color, thickness)
+
+    # Bottom-left corner
+    cv2.line(image, (x1, y2), (x1, y2 - corner_length), color, thickness)
+    cv2.line(image, (x1, y2), (x1 + corner_length, y2), color, thickness)
+
+    # Bottom-right corner
+    cv2.line(image, (x2, y2), (x2, y2 - corner_length), color, thickness)
+    cv2.line(image, (x2, y2), (x2 - corner_length, y2), color, thickness)