Merge pull request #23 from yakhyo/test-files-update

feat: Some minor changes to code style and warning supression

README.md

@@ -394,12 +394,28 @@ 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
 
 ```

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uniface"
-version = "1.1.0"
+version = "1.1.1"
 description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection"
 readme = "README.md"
 license = { text = "MIT" }
@@ -19,7 +19,7 @@ dependencies = [
 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"]
 
 [project.urls]
@@ -35,3 +35,13 @@ packages = { find = {} }
 
 [tool.setuptools.package-data]
 "uniface" = ["*.txt", "*.md"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["uniface"]

scripts/README.md

@@ -1,97 +1,68 @@
 # Scripts
 
-Collection of example scripts demonstrating UniFace functionality.
+Scripts for testing UniFace features.
 
 ## Available Scripts
 
-- `run_detection.py` - Face detection on images
-- `run_age_gender.py` - Age and gender prediction
-- `run_landmarks.py` - Facial landmark detection
-- `run_recognition.py` - Face recognition and embeddings
-- `run_face_search.py` - Face search and matching
-- `run_video_detection.py` - Video processing with face detection
-- `batch_process.py` - Batch processing of image folders
-- `download_model.py` - Download and manage models
+| Script | Description |
+|--------|-------------|
+| `run_detection.py` | Face detection on image or webcam |
+| `run_age_gender.py` | Age and gender prediction |
+| `run_landmarks.py` | 106-point facial landmark detection |
+| `run_recognition.py` | Face embedding extraction and comparison |
+| `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 |
 
-## Quick Start
+## Usage Examples
 
 ```bash
 # Face detection
 python scripts/run_detection.py --image assets/test.jpg
+python scripts/run_detection.py --webcam
 
-# Age and gender detection
+# Age and gender
 python scripts/run_age_gender.py --image assets/test.jpg
-
-# Webcam demo
 python scripts/run_age_gender.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
 ```
 
-## Import Examples
-
-The scripts use direct class imports for better developer experience:
-
-```python
-# Face Detection
-from uniface.detection import RetinaFace, SCRFD
-
-detector = RetinaFace()  # or SCRFD()
-faces = detector.detect(image)
-
-# Face Recognition
-from uniface.recognition import ArcFace, MobileFace, SphereFace
-
-recognizer = ArcFace()  # or MobileFace(), SphereFace()
-embedding = recognizer.get_embedding(image, landmarks)
-
-# Age & Gender
-from uniface.attribute import AgeGender
-
-age_gender = AgeGender()
-gender, age = age_gender.predict(image, bbox)
-
-# Landmarks
-from uniface.landmark import Landmark106
-
-landmarker = Landmark106()
-landmarks = landmarker.get_landmarks(image, bbox)
-```
-
-## Available Classes
-
-**Detection:**
-- `RetinaFace` - High accuracy face detection
-- `SCRFD` - Fast face detection
-
-**Recognition:**
-- `ArcFace` - High accuracy face recognition
-- `MobileFace` - Lightweight face recognition
-- `SphereFace` - Alternative face recognition
-
-**Attributes:**
-- `AgeGender` - Age and gender prediction
-
-**Landmarks:**
-- `Landmark106` - 106-point facial landmarks
-
 ## Common Options
 
-Most scripts support:
-- `--help` - Show usage information
-- `--verbose` - Enable detailed logging
-- `--detector` - Choose detector (retinaface, scrfd)
-- `--threshold` - Set confidence threshold
+| Option | Description |
+|--------|-------------|
+| `--image` | Path to input image |
+| `--webcam` | Use webcam instead of image |
+| `--detector` | Choose detector: `retinaface` or `scrfd` |
+| `--threshold` | Visualization confidence threshold (default: 0.6) |
+| `--save_dir` | Output directory (default: `outputs`) |
 
-## Testing
+## Quick Test
 
-Run basic functionality test:
 ```bash
 python scripts/run_detection.py --image assets/test.jpg
 ```
-
-For comprehensive testing, see the main project tests:
-```bash
-pytest tests/
-```

scripts/batch_process.py

@@ -1,156 +1,95 @@
-"""Batch Image Processing Script"""
+# Batch face detection on a folder of images
+# Usage: python batch_process.py --input images/ --output results/
 
-import os
-import cv2
 import argparse
 from pathlib import Path
+
+import cv2
 from tqdm import tqdm
 
-from uniface import RetinaFace, SCRFD
+from uniface import SCRFD, RetinaFace
 from uniface.visualization import draw_detections
 
 
 def get_image_files(input_dir: Path, extensions: tuple) -> list:
-    image_files = []
+    files = []
     for ext in extensions:
-        image_files.extend(input_dir.glob(f"*.{ext}"))
-        image_files.extend(input_dir.glob(f"*.{ext.upper()}"))
-
-    return sorted(image_files)
+        files.extend(input_dir.glob(f"*.{ext}"))
+        files.extend(input_dir.glob(f"*.{ext.upper()}"))
+    return sorted(files)
 
 
-def process_single_image(detector, image_path: Path, output_dir: Path,
-                        vis_threshold: float, skip_existing: bool) -> dict:
-    output_path = output_dir / f"{image_path.stem}_detected{image_path.suffix}"
-
-    # Skip if already processed
-    if skip_existing and output_path.exists():
-        return {"status": "skipped", "faces": 0}
-
-    # Load image
+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 {"status": "error", "error": "Failed to load image"}
+        return -1
 
-    # Detect faces
-    try:
-        faces = detector.detect(image)
-    except Exception as e:
-        return {"status": "error", "error": str(e)}
+    faces = detector.detect(image)
 
-    # Draw detections
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
-    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+    # 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, bboxes, scores, landmarks, vis_threshold=threshold)
 
-    # Add face count
-    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
-               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-    # Save result
+    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 {"status": "success", "faces": len(faces)}
-
-
-def batch_process(detector, input_dir: str, output_dir: str, extensions: tuple,
-                 vis_threshold: float, skip_existing: bool):
-    input_path = Path(input_dir)
-    output_path = Path(output_dir)
-
-    # Create output directory
-    output_path.mkdir(parents=True, exist_ok=True)
-
-    # Get image files
-    image_files = get_image_files(input_path, extensions)
-
-    if not image_files:
-        print(f"No image files found in '{input_dir}' with extensions {extensions}")
-        return
-
-    print(f"Input: {input_dir}")
-    print(f"Output: {output_dir}")
-    print(f"Found {len(image_files)} images\n")
-
-    # Process images
-    results = {
-        "success": 0,
-        "skipped": 0,
-        "error": 0,
-        "total_faces": 0
-    }
-
-    with tqdm(image_files, desc="Processing images", unit="img") as pbar:
-        for image_path in pbar:
-            result = process_single_image(
-                detector, image_path, output_path,
-                vis_threshold, skip_existing
-            )
-
-            if result["status"] == "success":
-                results["success"] += 1
-                results["total_faces"] += result["faces"]
-                pbar.set_postfix({"faces": result["faces"]})
-            elif result["status"] == "skipped":
-                results["skipped"] += 1
-            else:
-                results["error"] += 1
-                print(f"\nError processing {image_path.name}: {result.get('error', 'Unknown error')}")
-
-    # Print summary
-    print(f"\nBatch processing complete!")
-    print(f"   Total images: {len(image_files)}")
-    print(f"   Successfully processed: {results['success']}")
-    print(f"   Skipped: {results['skipped']}")
-    print(f"   Errors: {results['error']}")
-    print(f"   Total faces detected: {results['total_faces']}")
-    if results['success'] > 0:
-        print(f"   Average faces per image: {results['total_faces']/results['success']:.2f}")
-    print(f"\nResults saved to: {output_dir}")
+    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 containing images")
-    parser.add_argument("--output", type=str, required=True,
-                       help="Output directory for processed images")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    parser.add_argument("--extensions", type=str, default="jpg,jpeg,png,bmp",
-                       help="Comma-separated list of image extensions")
-    parser.add_argument("--skip_existing", action="store_true",
-                       help="Skip files that already exist in output directory")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
+    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()
 
-    # Check input directory exists
-    if not Path(args.input).exists():
+    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
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
+    output_path.mkdir(parents=True, exist_ok=True)
 
-    # Parse extensions
-    extensions = tuple(ext.strip() for ext in args.extensions.split(','))
+    extensions = tuple(ext.strip() for ext in args.extensions.split(","))
+    image_files = get_image_files(input_path, extensions)
 
-    # Initialize detector
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-    print("Detector initialized\n")
+    if not image_files:
+        print(f"No images found with extensions {extensions}")
+        return
 
-    # Process batch
-    batch_process(detector, args.input, args.output, extensions,
-                 args.threshold, args.skip_existing)
+    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__":

scripts/download_model.py

@@ -1,76 +1,59 @@
 import argparse
+
 from uniface.constants import (
-    RetinaFaceWeights, SphereFaceWeights, MobileFaceWeights, ArcFaceWeights,
-    SCRFDWeights, DDAMFNWeights, AgeGenderWeights, LandmarkWeights
+    AgeGenderWeights,
+    ArcFaceWeights,
+    DDAMFNWeights,
+    LandmarkWeights,
+    MobileFaceWeights,
+    RetinaFaceWeights,
+    SCRFDWeights,
+    SphereFaceWeights,
 )
 from uniface.model_store import verify_model_weights
 
-
-# All available model types
-ALL_MODEL_TYPES = {
-    'retinaface': RetinaFaceWeights,
-    'sphereface': SphereFaceWeights,
-    'mobileface': MobileFaceWeights,
-    'arcface': ArcFaceWeights,
-    'scrfd': SCRFDWeights,
-    'ddamfn': DDAMFNWeights,
-    'agegender': AgeGenderWeights,
-    'landmark': LandmarkWeights,
+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 model weights.")
+    parser = argparse.ArgumentParser(description="Download model weights")
     parser.add_argument(
         "--model-type",
         type=str,
-        choices=list(ALL_MODEL_TYPES.keys()),
-        help="Model type to download (e.g. retinaface, arcface). If not specified, all models will be downloaded.",
-    )
-    parser.add_argument(
-        "--model",
-        type=str,
-        help="Specific model to download (e.g. MNET_V2). For RetinaFace backward compatibility.",
+        choices=list(MODEL_TYPES.keys()),
+        help="Model type to download. If not specified, downloads all.",
     )
     args = parser.parse_args()
 
-    if args.model and not args.model_type:
-        # Backward compatibility - assume RetinaFace
-        try:
-            weight = RetinaFaceWeights[args.model]
-            print(f"Downloading RetinaFace model: {weight.value}")
-            verify_model_weights(weight)
-            print("Model downloaded successfully.")
-        except KeyError:
-            print(f"Invalid RetinaFace model: {args.model}")
-            print(f"Available models: {[m.name for m in RetinaFaceWeights]}")
-        return
-
     if args.model_type:
-        # Download all models from specific type
-        model_enum = ALL_MODEL_TYPES[args.model_type]
-        print(f"Downloading all {args.model_type} models...")
-        for weight in model_enum:
-            print(f"Downloading: {weight.value}")
-            try:
-                verify_model_weights(weight)
-                print(f"Downloaded: {weight.value}")
-            except Exception as e:
-                print(f"Failed to download {weight.value}: {e}")
+        print(f"Downloading {args.model_type} models...")
+        download_models(MODEL_TYPES[args.model_type])
     else:
-        # Download all models from all types
         print("Downloading all models...")
-        for model_type, model_enum in ALL_MODEL_TYPES.items():
-            print(f"\nDownloading {model_type} models...")
-            for weight in model_enum:
-                print(f"Downloading: {weight.value}")
-                try:
-                    verify_model_weights(weight)
-                    print(f"Downloaded: {weight.value}")
-                except Exception as e:
-                    print(f"Failed to download {weight.value}: {e}")
+        for name, model_enum in MODEL_TYPES.items():
+            print(f"\n{name}:")
+            download_models(model_enum)
 
-    print("\nDownload process completed.")
+    print("\nDone!")
 
 
 if __name__ == "__main__":

scripts/run_age_gender.py

@@ -1,158 +1,119 @@
-"""Age and Gender Detection Demo Script"""
+# 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 os
-import cv2
 import argparse
+import os
 from pathlib import Path
 
-from uniface import RetinaFace, SCRFD, AgeGender
+import cv2
+
+from uniface import SCRFD, AgeGender, RetinaFace
 from uniface.visualization import draw_detections
 
 
-def process_image(detector, age_gender, image_path: str, save_dir: str = "outputs", vis_threshold: float = 0.6):
+def draw_age_gender_label(image, bbox, gender: str, age: int):
+    """Draw age/gender label above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    text = f"{gender}, {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
 
-    print(f"Processing: {image_path}")
-
-    # Detect faces
     faces = detector.detect(image)
-    print(f"  Detected {len(faces)} face(s)")
+    print(f"Detected {len(faces)} face(s)")
 
     if not faces:
-        print("  No faces detected")
         return
 
-    # Draw detections
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
-    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
+    bboxes = [f["bbox"] for f in faces]
+    scores = [f["confidence"] for f in faces]
+    landmarks = [f["landmarks"] for f in faces]
+    draw_detections(image, bboxes, scores, landmarks, vis_threshold=threshold)
 
-    # Predict and draw age/gender for each face
     for i, face in enumerate(faces):
-        gender, age = age_gender.predict(image, face['bbox'])
-        print(f"  Face {i+1}: {gender}, {age} years old")
+        gender, age = age_gender.predict(image, face["bbox"])
+        print(f"  Face {i + 1}: {gender}, {age} years old")
+        draw_age_gender_label(image, face["bbox"], gender, age)
 
-        # Draw age and gender text
-        bbox = face['bbox']
-        x1, y1 = int(bbox[0]), int(bbox[1])
-        text = f"{gender}, {age}y"
-
-        # Background rectangle for text
-        (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
-        cv2.rectangle(image, (x1, y1 - text_height - 10),
-                    (x1 + text_width + 10, y1), (0, 255, 0), -1)
-        cv2.putText(image, text, (x1 + 5, y1 - 5),
-                   cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
-
-    # Save result
     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, vis_threshold: float = 0.6):
-    cap = cv2.VideoCapture(0)
-
+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("Webcam opened")
-    print("Press 'q' to quit\n")
+    print("Press 'q' to quit")
 
-    frame_count = 0
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
 
-    try:
-        while True:
-            ret, frame = cap.read()
-            if not ret:
-                break
+        faces = detector.detect(frame)
 
-            frame_count += 1
+        # 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)
 
-            # Detect faces
-            faces = detector.detect(frame)
+        for face in faces:
+            gender, age = age_gender.predict(frame, face["bbox"])  # predict per face
+            draw_age_gender_label(frame, face["bbox"], gender, age)
 
-            # Draw detections
-            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=vis_threshold)
+        cv2.putText(
+            frame,
+            f"Faces: {len(faces)}",
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow("Age & Gender Detection", frame)
 
-            # Predict and draw age/gender for each face
-            for face in faces:
-                gender, age = age_gender.predict(frame, face['bbox'])
+        if cv2.waitKey(1) & 0xFF == ord("q"):
+            break
 
-                # Draw age and gender text
-                bbox = face['bbox']
-                x1, y1 = int(bbox[0]), int(bbox[1])
-                text = f"{gender}, {age}y"
-
-                # Background rectangle for text
-                (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
-                cv2.rectangle(frame, (x1, y1 - text_height - 10),
-                            (x1 + text_width + 10, y1), (0, 255, 0), -1)
-                cv2.putText(frame, text, (x1 + 5, y1 - 5),
-                           cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
-
-            # Add info
-            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
-                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
-
-            cv2.imshow("Age & Gender Detection", frame)
-
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-
-    except KeyboardInterrupt:
-        print("\nInterrupted")
-    finally:
-        cap.release()
-        cv2.destroyAllWindows()
-        print(f"\nProcessed {frame_count} frames")
+    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 instead of image")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    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.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()
 
-    # Validate input
     if not args.image and not args.webcam:
         parser.error("Either --image or --webcam must be specified")
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize models
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print("Initializing age/gender model...")
+    detector = RetinaFace() if args.detector == "retinaface" else SCRFD()
     age_gender = AgeGender()
-    print("Models initialized\n")
 
-    # Process
     if args.webcam:
         run_webcam(detector, age_gender, args.threshold)
     else:

scripts/run_detection.py

@@ -1,79 +1,94 @@
-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
 
-from uniface.detection import RetinaFace, SCRFD
+import argparse
+import os
+
+import cv2
+
+from uniface.detection import SCRFD, RetinaFace
 from uniface.visualization import draw_detections
 
 
-def run_inference(detector, image_path: str, vis_threshold: float = 0.6, save_dir: str = "outputs"):
+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}'")
         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)
-
+        bboxes = [face["bbox"] for face in faces]
+        scores = [face["confidence"] for face in faces]
+        landmarks = [face["landmarks"] for face in faces]
+        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")
     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(frame, bboxes, scores, landmarks, vis_threshold=threshold)
+
+        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"])
+    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 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}")
-    if args.method == 'retinaface':
-        detector = RetinaFace()
+    detector = RetinaFace() if args.method == "retinaface" else SCRFD()
+
+    if args.webcam:
+        run_webcam(detector, args.threshold)
     else:
-        detector = SCRFD()
-
-    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
-
-    if args.iterations > 1:
-        # Adjust average calculation to exclude potential first-run overhead
-        effective_iterations = max(1, args.iterations)
-        print(
-            f"\nAverage inference time over {effective_iterations} runs: {avg_time / effective_iterations:.4f} seconds")
+        process_image(detector, args.image, args.threshold, args.save_dir)
 
 
 if __name__ == "__main__":

scripts/run_face_search.py

@@ -1,13 +1,25 @@
+# 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
 
-from uniface.detection import RetinaFace, SCRFD
+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 extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
     image = cv2.imread(image_path)
     if image is None:
@@ -17,44 +29,37 @@ def extract_reference_embedding(detector, recognizer, image_path: str) -> np.nda
     if not faces:
         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
+    return recognizer.get_normalized_embedding(image, landmarks)
 
 
-def run_video(detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
-    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.")
+
+    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"])
-
             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
+            # 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)
 
@@ -67,43 +72,25 @@ 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.add_argument(
-        "--detector", type=str, default="scrfd", choices=["retinaface", "scrfd"], help="Face detection method."
-    )
+    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(
         "--recognizer",
         type=str,
         default="arcface",
         choices=["arcface", "mobileface", "sphereface"],
-        help="Face recognition method.",
     )
-    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...")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    if args.recognizer == 'arcface':
-        recognizer = ArcFace()
-    elif args.recognizer == 'mobileface':
-        recognizer = MobileFace()
-    else:
-        recognizer = SphereFace()
-
-    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__":

scripts/run_landmarks.py

@@ -1,11 +1,14 @@
-"""Facial Landmark Detection Demo Script"""
+# 106-point facial landmark detection
+# Usage: python run_landmarks.py --image path/to/image.jpg
+#        python run_landmarks.py --webcam
 
-import os
-import cv2
 import argparse
+import os
 from pathlib import Path
 
-from uniface import RetinaFace, SCRFD, Landmark106
+import cv2
+
+from uniface import SCRFD, Landmark106, RetinaFace
 
 
 def process_image(detector, landmarker, image_path: str, save_dir: str = "outputs"):
@@ -14,39 +17,33 @@ def process_image(detector, landmarker, image_path: str, save_dir: str = "output
         print(f"Error: Failed to load image from '{image_path}'")
         return
 
-    print(f"Processing: {image_path}")
-
-    # Detect faces
     faces = detector.detect(image)
-    print(f"  Detected {len(faces)} face(s)")
+    print(f"Detected {len(faces)} face(s)")
 
     if not faces:
-        print("  No faces detected")
         return
 
-    # Process each face
     for i, face in enumerate(faces):
-        # Draw bounding box
-        bbox = face['bbox']
+        bbox = face["bbox"]
         x1, y1, x2, y2 = map(int, bbox)
         cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
 
-        # Get and draw 106 landmarks
         landmarks = landmarker.get_landmarks(image, bbox)
-        print(f"  Face {i+1}: Extracted {len(landmarks)} landmarks")
+        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)
 
-        # Add face count
-        cv2.putText(image, f"Face {i+1}", (x1, y1 - 10),
-                   cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+        cv2.putText(
+            image,
+            f"Face {i + 1}",
+            (x1, y1 - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (0, 255, 0),
+            2,
+        )
 
-    # Add total count
-    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
-               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-    # Save result
     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)
@@ -54,91 +51,62 @@ def process_image(detector, landmarker, image_path: str, save_dir: str = "output
 
 
 def run_webcam(detector, landmarker):
-    cap = cv2.VideoCapture(0)
-
+    cap = cv2.VideoCapture(0)  # 0 = default webcam
     if not cap.isOpened():
         print("Cannot open webcam")
         return
 
-    print("Webcam opened")
-    print("Press 'q' to quit\n")
+    print("Press 'q' to quit")
 
-    frame_count = 0
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
 
-    try:
-        while True:
-            ret, frame = cap.read()
-            if not ret:
-                break
+        faces = detector.detect(frame)
 
-            frame_count += 1
+        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)
 
-            # Detect faces
-            faces = detector.detect(frame)
+            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)
 
-            # Process each face
-            for face in faces:
-                # Draw bounding box
-                bbox = face['bbox']
-                x1, y1, x2, y2 = map(int, bbox)
-                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+        cv2.putText(
+            frame,
+            f"Faces: {len(faces)}",
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        cv2.imshow("106-Point Landmarks", frame)
 
-                # Get and draw 106 landmarks
-                landmarks = landmarker.get_landmarks(frame, bbox)
-                for x, y in landmarks.astype(int):
-                    cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
+        if cv2.waitKey(1) & 0xFF == ord("q"):
+            break
 
-            # Add info
-            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
-                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
-
-            cv2.imshow("106-Point Landmarks", frame)
-
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-
-    except KeyboardInterrupt:
-        print("\nInterrupted")
-    finally:
-        cap.release()
-        cv2.destroyAllWindows()
-        print(f"\nProcessed {frame_count} frames")
+    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 instead of image")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    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.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()
 
-    # Validate input
     if not args.image and not args.webcam:
         parser.error("Either --image or --webcam must be specified")
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize models
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print("Initializing landmark detector...")
+    detector = RetinaFace() if args.detector == "retinaface" else SCRFD()
     landmarker = Landmark106()
-    print("Models initialized\n")
 
-    # Process
     if args.webcam:
         run_webcam(detector, landmarker)
     else:

scripts/run_recognition.py

@@ -1,10 +1,24 @@
-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
 
-from uniface.detection import RetinaFace, SCRFD
-from uniface.recognition import ArcFace, MobileFace, SphereFace
+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):
@@ -14,38 +28,29 @@ def run_inference(detector, recognizer, image_path: str):
         return
 
     faces = detector.detect(image)
-
     if not faces:
         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 = np.array(faces[0]["landmarks"])  # 5-point landmarks for alignment
     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):
-
-    # Load images
     img1 = cv2.imread(image1_path)
     img2 = cv2.imread(image2_path)
 
     if img1 is None or img2 is None:
-        print(f"Error: Failed to load images")
+        print("Error: Failed to load one or both images")
         return
 
-    # Detect faces
     faces1 = detector.detect(img1)
     faces2 = detector.detect(img2)
 
@@ -53,74 +58,44 @@ def compare_faces(detector, recognizer, image1_path: str, image2_path: str, thre
         print("Error: No faces detected in one or both images")
         return
 
-    # Get landmarks for first face in each image
-    landmarks1 = np.array(faces1[0]['landmarks'])
-    landmarks2 = np.array(faces2[0]['landmarks'])
+    landmarks1 = np.array(faces1[0]["landmarks"])
+    landmarks2 = np.array(faces2[0]["landmarks"])
 
-    # Get normalized embeddings
     embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
     embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)
 
-    # Compute similarity
+    # 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'}")
-    print(f"Threshold: {threshold}")
+    print(f"Result: {'Same person' if is_match else 'Different person'} (threshold: {threshold})")
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Face recognition and comparison.")
-    parser.add_argument("--image", type=str, help="Path to single image for embedding extraction.")
-    parser.add_argument("--image1", type=str, help="Path to first image for comparison.")
-    parser.add_argument("--image2", type=str, help="Path to second image for comparison.")
-    parser.add_argument("--threshold", type=float, default=0.35, help="Similarity threshold for face matching.")
-    parser.add_argument(
-        "--detector",
-        type=str,
-        default="retinaface",
-        choices=['retinaface', 'scrfd'],
-        help="Face detection method to use."
-    )
+    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(
         "--recognizer",
         type=str,
         default="arcface",
-        choices=['arcface', 'mobileface', 'sphereface'],
-        help="Face recognition method to use."
+        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
-        enable_logging()
-
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print(f"Initializing recognizer: {args.recognizer}")
-    if args.recognizer == 'arcface':
-        recognizer = ArcFace()
-    elif args.recognizer == 'mobileface':
-        recognizer = MobileFace()
-    else:
-        recognizer = SphereFace()
+    detector = RetinaFace() if args.detector == "retinaface" else SCRFD()
+    recognizer = get_recognizer(args.recognizer)
 
     if args.image1 and args.image2:
-        # Face comparison mode
-        print(f"Comparing faces: {args.image1} vs {args.image2}")
         compare_faces(detector, recognizer, args.image1, args.image2, args.threshold)
     elif args.image:
-        # Single image embedding extraction mode
         run_inference(detector, recognizer, args.image)
     else:
-        print("Error: Provide either --image for single image processing or --image1 and --image2 for comparison")
+        print("Error: Provide --image or both --image1 and --image2")
         parser.print_help()
 
 

scripts/run_video_detection.py

@@ -1,141 +1,106 @@
-"""Video Face Detection Script"""
+# Face detection on video files
+# Usage: python run_video_detection.py --input video.mp4 --output output.mp4
 
-import cv2
 import argparse
 from pathlib import Path
+
+import cv2
 from tqdm import tqdm
 
-from uniface import RetinaFace, SCRFD
+from uniface import SCRFD, RetinaFace
 from uniface.visualization import draw_detections
 
 
-def process_video(detector, input_path: str, output_path: str, vis_threshold: float = 0.6,
-                 fps: int = None, show_preview: bool = False):
-    # Open input video
+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
+    # get video properties
     total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-    source_fps = cap.get(cv2.CAP_PROP_FPS)
+    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))
 
-    output_fps = fps if fps is not None else source_fps
+    print(f"Input: {input_path} ({width}x{height}, {fps:.1f} fps, {total_frames} frames)")
+    print(f"Output: {output_path}")
 
-    print(f"📹 Input: {input_path}")
-    print(f"   Resolution: {width}x{height}")
-    print(f"   FPS: {source_fps:.2f}")
-    print(f"   Total frames: {total_frames}")
-    print(f"\n📹 Output: {output_path}")
-    print(f"   FPS: {output_fps:.2f}\n")
-
-    # Initialize video writer
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    out = cv2.VideoWriter(output_path, fourcc, output_fps, (width, height))
+    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
 
-    # Process frames
     frame_count = 0
     total_faces = 0
 
-    try:
-        with tqdm(total=total_frames, desc="Processing", unit="frames") as pbar:
-            while True:
-                ret, frame = cap.read()
-                if not ret:
-                    break
+    for _ in tqdm(range(total_frames), desc="Processing", unit="frames"):
+        ret, frame = cap.read()
+        if not ret:
+            break
 
-                frame_count += 1
+        frame_count += 1
+        faces = detector.detect(frame)
+        total_faces += len(faces)
 
-                # Detect faces
-                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(frame, bboxes, scores, landmarks, vis_threshold=threshold)
 
-                # Draw detections
-                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=vis_threshold)
+        cv2.putText(
+            frame,
+            f"Faces: {len(faces)}",
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 255, 0),
+            2,
+        )
+        out.write(frame)
 
-                # Add frame info
-                cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                           cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-                # Write frame
-                out.write(frame)
-
-                # Show preview if requested
-                if show_preview:
-                    cv2.imshow("Processing Video - Press 'q' to cancel", frame)
-                    if cv2.waitKey(1) & 0xFF == ord('q'):
-                        print("\nProcessing cancelled by user")
-                        break
-
-                pbar.update(1)
-
-    except KeyboardInterrupt:
-        print("\nProcessing interrupted")
-    finally:
-        cap.release()
-        out.release()
         if show_preview:
-            cv2.destroyAllWindows()
+            cv2.imshow("Processing - Press 'q' to cancel", frame)
+            if cv2.waitKey(1) & 0xFF == ord("q"):
+                print("\nCancelled by user")
+                break
 
-    # Summary
-    print(f"\nProcessing complete!")
-    print(f"   Processed: {frame_count} frames")
-    print(f"   Total faces detected: {total_faces}")
-    print(f"   Average faces per frame: {total_faces/frame_count:.2f}" if frame_count > 0 else "")
-    print(f"   Output saved: {output_path}")
+    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="Path to input video")
-    parser.add_argument("--output", type=str, required=True, help="Path to output video")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    parser.add_argument("--fps", type=int, default=None,
-                       help="Output FPS (default: same as input)")
-    parser.add_argument("--preview", action="store_true",
-                       help="Show live preview during processing")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
+    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()
 
-    # Check input exists
     if not Path(args.input).exists():
         print(f"Error: Input file '{args.input}' does not exist")
         return
 
-    # Create output directory if needed
-    output_dir = Path(args.output).parent
-    if output_dir != Path('.'):
-        output_dir.mkdir(parents=True, exist_ok=True)
+    Path(args.output).parent.mkdir(parents=True, exist_ok=True)
 
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize detector
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-    print("Detector initialized\n")
-
-    # Process video
-    process_video(detector, args.input, args.output, args.threshold, args.fps, args.preview)
+    detector = RetinaFace() if args.detector == "retinaface" else SCRFD()
+    process_video(detector, args.input, args.output, args.threshold, args.preview)
 
 
 if __name__ == "__main__":

scripts/sha256_generate.py

@@ -12,15 +12,8 @@ def compute_sha256(file_path: Path, chunk_size: int = 8192) -> str:
 
 
 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():
@@ -28,7 +21,7 @@ def main():
         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__":

tests/test_age_gender.py

@@ -31,7 +31,7 @@ def test_prediction_output_format(age_gender_model, mock_image, mock_bbox):
 
 def test_gender_values(age_gender_model, mock_image, mock_bbox):
     gender, age = age_gender_model.predict(mock_image, mock_bbox)
-    assert gender in ['Male', 'Female'], f"Gender should be 'Male' or 'Female', got '{gender}'"
+    assert gender in ["Male", "Female"], f"Gender should be 'Male' or 'Female', got '{gender}'"
 
 
 def test_age_range(age_gender_model, mock_image, mock_bbox):
@@ -48,7 +48,7 @@ def test_different_bbox_sizes(age_gender_model, mock_image):
 
     for bbox in test_bboxes:
         gender, age = age_gender_model.predict(mock_image, bbox)
-        assert gender in ['Male', 'Female'], f"Failed for bbox {bbox}"
+        assert gender in ["Male", "Female"], f"Failed for bbox {bbox}"
         assert 0 <= age <= 120, f"Age out of range for bbox {bbox}"
 
 
@@ -58,7 +58,7 @@ def test_different_image_sizes(age_gender_model, mock_bbox):
     for size in test_sizes:
         mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
         gender, age = age_gender_model.predict(mock_image, mock_bbox)
-        assert gender in ['Male', 'Female'], f"Failed for image size {size}"
+        assert gender in ["Male", "Female"], f"Failed for image size {size}"
         assert 0 <= age <= 120, f"Age out of range for image size {size}"
 
 
@@ -73,14 +73,14 @@ def test_consistency(age_gender_model, mock_image, mock_bbox):
 def test_bbox_list_format(age_gender_model, mock_image):
     bbox_list = [100, 100, 300, 300]
     gender, age = age_gender_model.predict(mock_image, bbox_list)
-    assert gender in ['Male', 'Female'], "Should work with bbox as list"
+    assert gender in ["Male", "Female"], "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, age = age_gender_model.predict(mock_image, bbox_array)
-    assert gender in ['Male', 'Female'], "Should work with bbox as numpy array"
+    assert gender in ["Male", "Female"], "Should work with bbox as numpy array"
     assert 0 <= age <= 120, "Age should be in valid range"
 
 
@@ -98,7 +98,7 @@ def test_multiple_predictions(age_gender_model, mock_image):
 
     assert len(results) == 3, "Should have 3 predictions"
     for gender, age in results:
-        assert gender in ['Male', 'Female']
+        assert gender in ["Male", "Female"]
         assert 0 <= age <= 120
 
 

tests/test_factory.py

@@ -16,7 +16,7 @@ def test_create_detector_retinaface():
     """
     Test creating a RetinaFace detector using factory function.
     """
-    detector = create_detector('retinaface')
+    detector = create_detector("retinaface")
     assert detector is not None, "Failed to create RetinaFace detector"
 
 
@@ -24,7 +24,7 @@ def test_create_detector_scrfd():
     """
     Test creating a SCRFD detector using factory function.
     """
-    detector = create_detector('scrfd')
+    detector = create_detector("scrfd")
     assert detector is not None, "Failed to create SCRFD detector"
 
 
@@ -33,10 +33,10 @@ def test_create_detector_with_config():
     Test creating detector with custom configuration.
     """
     detector = create_detector(
-        'retinaface',
+        "retinaface",
         model_name=RetinaFaceWeights.MNET_V2,
         conf_thresh=0.8,
-        nms_thresh=0.3
+        nms_thresh=0.3,
     )
     assert detector is not None, "Failed to create detector with custom config"
 
@@ -46,18 +46,14 @@ def test_create_detector_invalid_method():
     Test that invalid detector method raises an error.
     """
     with pytest.raises((ValueError, KeyError)):
-        create_detector('invalid_method')
+        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
-    )
+    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"
 
 
@@ -66,7 +62,7 @@ def test_create_recognizer_arcface():
     """
     Test creating an ArcFace recognizer using factory function.
     """
-    recognizer = create_recognizer('arcface')
+    recognizer = create_recognizer("arcface")
     assert recognizer is not None, "Failed to create ArcFace recognizer"
 
 
@@ -74,7 +70,7 @@ def test_create_recognizer_mobileface():
     """
     Test creating a MobileFace recognizer using factory function.
     """
-    recognizer = create_recognizer('mobileface')
+    recognizer = create_recognizer("mobileface")
     assert recognizer is not None, "Failed to create MobileFace recognizer"
 
 
@@ -82,7 +78,7 @@ def test_create_recognizer_sphereface():
     """
     Test creating a SphereFace recognizer using factory function.
     """
-    recognizer = create_recognizer('sphereface')
+    recognizer = create_recognizer("sphereface")
     assert recognizer is not None, "Failed to create SphereFace recognizer"
 
 
@@ -91,7 +87,7 @@ def test_create_recognizer_invalid_method():
     Test that invalid recognizer method raises an error.
     """
     with pytest.raises((ValueError, KeyError)):
-        create_recognizer('invalid_method')
+        create_recognizer("invalid_method")
 
 
 # create_landmarker tests
@@ -99,7 +95,7 @@ def test_create_landmarker():
     """
     Test creating a Landmark106 detector using factory function.
     """
-    landmarker = create_landmarker('2d106det')
+    landmarker = create_landmarker("2d106det")
     assert landmarker is not None, "Failed to create Landmark106 detector"
 
 
@@ -116,7 +112,7 @@ def test_create_landmarker_invalid_method():
     Test that invalid landmarker method raises an error.
     """
     with pytest.raises((ValueError, KeyError)):
-        create_landmarker('invalid_method')
+        create_landmarker("invalid_method")
 
 
 # detect_faces tests
@@ -125,7 +121,7 @@ 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')
+    faces = detect_faces(mock_image, method="retinaface")
 
     assert isinstance(faces, list), "detect_faces should return a list"
 
@@ -135,7 +131,7 @@ 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')
+    faces = detect_faces(mock_image, method="scrfd")
 
     assert isinstance(faces, list), "detect_faces should return a list"
 
@@ -145,13 +141,13 @@ 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)
+    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"
+        assert face["confidence"] >= 0.8, "All detections should meet confidence threshold"
 
 
 def test_detect_faces_default_method():
@@ -169,7 +165,7 @@ 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')
+    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"
@@ -193,8 +189,8 @@ def test_list_available_detectors_contents():
     detectors = list_available_detectors()
 
     # Should include at least these detectors
-    assert 'retinaface' in detectors, "Should include 'retinaface'"
-    assert 'scrfd' in detectors, "Should include 'scrfd'"
+    assert "retinaface" in detectors, "Should include 'retinaface'"
+    assert "scrfd" in detectors, "Should include 'scrfd'"
 
 
 # Integration tests
@@ -202,7 +198,7 @@ def test_detector_inference_from_factory():
     """
     Test that detector created from factory can perform inference.
     """
-    detector = create_detector('retinaface')
+    detector = create_detector("retinaface")
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
 
     faces = detector.detect(mock_image)
@@ -213,7 +209,7 @@ def test_recognizer_inference_from_factory():
     """
     Test that recognizer created from factory can perform inference.
     """
-    recognizer = create_recognizer('arcface')
+    recognizer = create_recognizer("arcface")
     mock_image = np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
 
     embedding = recognizer.get_embedding(mock_image)
@@ -225,7 +221,7 @@ def test_landmarker_inference_from_factory():
     """
     Test that landmarker created from factory can perform inference.
     """
-    landmarker = create_landmarker('2d106det')
+    landmarker = create_landmarker("2d106det")
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     mock_bbox = [100, 100, 300, 300]
 
@@ -238,8 +234,8 @@ def test_multiple_detector_creation():
     """
     Test that multiple detectors can be created independently.
     """
-    detector1 = create_detector('retinaface')
-    detector2 = create_detector('scrfd')
+    detector1 = create_detector("retinaface")
+    detector2 = create_detector("scrfd")
 
     assert detector1 is not None
     assert detector2 is not None
@@ -250,8 +246,8 @@ 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)
+    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)
 
@@ -269,9 +265,9 @@ def test_factory_returns_correct_types():
     """
     from uniface import RetinaFace, ArcFace, Landmark106
 
-    detector = create_detector('retinaface')
-    recognizer = create_recognizer('arcface')
-    landmarker = create_landmarker('2d106det')
+    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"

tests/test_recognition.py

@@ -41,13 +41,16 @@ 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)
+    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
@@ -173,8 +176,7 @@ def test_different_models_different_embeddings(arcface_model, mobileface_model,
 
     # 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"
+    assert not np.allclose(arcface_emb, mobileface_emb), "Different models should produce different embeddings"
 
 
 def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
@@ -191,6 +193,7 @@ def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
 
     # Compute cosine similarity
     from uniface import compute_similarity
+
     similarity = compute_similarity(emb1, emb2)
 
     # Similarity should be between -1 and 1
@@ -205,6 +208,7 @@ def test_same_face_high_similarity(arcface_model, 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

tests/test_utils.py

@@ -18,13 +18,16 @@ 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)
+    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
@@ -166,7 +169,7 @@ def test_face_alignment_landmarks_as_list(mock_image):
         [73.5318, 51.5014],
         [56.0252, 71.7366],
         [41.5493, 92.3655],
-        [70.7299, 92.2041]
+        [70.7299, 92.2041],
     ]
 
     # Convert list to numpy array before passing to face_alignment
@@ -201,9 +204,18 @@ def test_face_alignment_from_different_positions(mock_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),
+        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:
@@ -216,13 +228,16 @@ 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)
+    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"

uniface/__init__.py

@@ -13,7 +13,7 @@
 
 __license__ = "MIT"
 __author__ = "Yakhyokhuja Valikhujaev"
-__version__ = "1.1.0"
+__version__ = "1.1.1"
 
 
 from uniface.face_utils import compute_similarity, face_alignment
@@ -22,11 +22,18 @@ from uniface.model_store import verify_model_weights
 from uniface.visualization import draw_detections
 
 from .attribute import AgeGender
+
 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,
+    create_detector,
+    detect_faces,
+    list_available_detectors,
+)
 from .landmark import Landmark106, create_landmarker
 from .recognition import ArcFace, MobileFace, SphereFace, create_recognizer
 

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.
@@ -91,16 +84,16 @@ def predict_attributes(
     """
     for face in detections:
         # Initialize attributes dict if it doesn't exist
-        if 'attributes' not in face:
-            face['attributes'] = {}
+        if "attributes" not in face:
+            face["attributes"] = {}
 
         if isinstance(predictor, AgeGender):
-            gender, age = predictor(image, face['bbox'])
-            face['attributes']['gender'] = gender
-            face['attributes']['age'] = age
+            gender, age = predictor(image, face["bbox"])
+            face["attributes"]["gender"] = gender
+            face["attributes"]["age"] = age
         elif isinstance(predictor, Emotion):
-            emotion, confidence = predictor(image, face['landmark'])
-            face['attributes']['emotion'] = emotion
-            face['attributes']['confidence'] = confidence
+            emotion, confidence = predictor(image, face["landmark"])
+            face["attributes"]["emotion"] = emotion
+            face["attributes"]["confidence"] = confidence
 
     return detections

uniface/attribute/age_gender.py

@@ -51,8 +51,11 @@ class AgeGender(Attribute):
             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}")
         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:
         """
@@ -76,7 +79,11 @@ 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
 
@@ -157,7 +164,15 @@ if __name__ == "__main__":
             # Prepare text and draw on the frame
             label = f"{gender}, {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)

uniface/attribute/base.py

@@ -4,6 +4,7 @@
 
 from abc import ABC, abstractmethod
 from typing import Any
+
 import numpy as np
 
 

uniface/attribute/emotion.py

@@ -2,15 +2,16 @@
 # 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"]
@@ -43,7 +44,15 @@ class Emotion(Attribute):
         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")
 
@@ -63,7 +72,7 @@ class Emotion(Attribute):
             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 +86,7 @@ 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
@@ -115,8 +124,8 @@ class Emotion(Attribute):
 
 # TODO: below is only for testing, remove it later
 if __name__ == "__main__":
-    from uniface.detection import create_detector
     from uniface.constants import RetinaFaceWeights
+    from uniface.detection import create_detector
 
     print("Initializing models for live inference...")
     # 1. Initialize the face detector
@@ -145,26 +154,34 @@ if __name__ == "__main__":
 
         # For each detected face, predict the emotion
         for detection in detections:
-            box = detection['bbox']
-            landmark = detection['landmarks']
+            box = detection["bbox"]
+            landmark = detection["landmarks"]
             x1, y1, x2, y2 = map(int, box)
 
             # Predict attributes using the landmark
             emotion, confidence = emotion_predictor.predict(frame, landmark)
-            
+
             # Prepare text and draw on the frame
             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)
 
         # 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/common.py

@@ -2,12 +2,12 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import cv2
-import math
 import itertools
-import numpy as np
+import math
+from typing import List, Tuple
 
-from typing import Tuple, List
+import cv2
+import numpy as np
 
 
 def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
@@ -59,12 +59,7 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
     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]

uniface/constants.py

@@ -5,6 +5,7 @@
 from enum import Enum
 from typing import Dict
 
+
 # fmt: off
 class SphereFaceWeights(str, Enum):
     """
@@ -82,83 +83,65 @@ class LandmarkWeights(str, Enum):
 
 
 MODEL_URLS: Dict[Enum, str] = {
-
     # RetinaFace
-    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',
-
+    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/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',
-
+    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/weights/sphere20.onnx',
-    SphereFaceWeights.SPHERE36: 'https://github.com/yakhyo/uniface/releases/download/weights/sphere36.onnx',
-
-
+    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/weights/w600k_mbf.onnx',
-    ArcFaceWeights.RESNET: 'https://github.com/yakhyo/uniface/releases/download/weights/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/weights/scrfd_10g_kps.onnx',
-    SCRFDWeights.SCRFD_500M_KPS: 'https://github.com/yakhyo/uniface/releases/download/weights/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",
     # DDAFM
-    DDAMFNWeights.AFFECNET7: 'https://github.com/yakhyo/uniface/releases/download/weights/affecnet7.script',
-    DDAMFNWeights.AFFECNET8: 'https://github.com/yakhyo/uniface/releases/download/weights/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/weights/genderage.onnx',
-
+    AgeGenderWeights.DEFAULT: "https://github.com/yakhyo/uniface/releases/download/weights/genderage.onnx",
     # Landmarks
-    LandmarkWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/weights/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:      'eeda7d23d9c2b40cf77fa8da8e895b5697465192648852216074679657f8ee8b',
-    MobileFaceWeights.MNET_V2:       '38b148284dd48cc898d5d4453104252fbdcbacc105fe3f0b80e78954d9d20d89',
-    MobileFaceWeights.MNET_V3_SMALL: 'd4acafa1039a82957aa8a9a1dac278a401c353a749c39df43de0e29cc1c127c3',
-    MobileFaceWeights.MNET_V3_LARGE: '0e48f8e11f070211716d03e5c65a3db35a5e917cfb5bc30552358629775a142a',
-
+    MobileFaceWeights.MNET_025: "eeda7d23d9c2b40cf77fa8da8e895b5697465192648852216074679657f8ee8b",
+    MobileFaceWeights.MNET_V2: "38b148284dd48cc898d5d4453104252fbdcbacc105fe3f0b80e78954d9d20d89",
+    MobileFaceWeights.MNET_V3_SMALL: "d4acafa1039a82957aa8a9a1dac278a401c353a749c39df43de0e29cc1c127c3",
+    MobileFaceWeights.MNET_V3_LARGE: "0e48f8e11f070211716d03e5c65a3db35a5e917cfb5bc30552358629775a142a",
     # SphereFace
-    SphereFaceWeights.SPHERE20: 'c02878cf658eb1861f580b7e7144b0d27cc29c440bcaa6a99d466d2854f14c9d',
-    SphereFaceWeights.SPHERE36: '13b3890cd5d7dec2b63f7c36fd7ce07403e5a0bbb701d9647c0289e6cbe7bb20',
-
-
+    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",
     # 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

@@ -3,18 +3,19 @@
 # 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
 
 # Global cache for detector instances
 _detector_cache: Dict[str, BaseDetector] = {}
 
 
-def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> List[Dict[str, Any]]:
+def detect_faces(image: np.ndarray, method: str = "retinaface", **kwargs) -> List[Dict[str, Any]]:
     """
     High-level face detection function.
 
@@ -38,7 +39,7 @@ 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)}"
 
@@ -50,7 +51,7 @@ def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> Lis
     return detector.detect(image)
 
 
-def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
+def create_detector(method: str = "retinaface", **kwargs) -> BaseDetector:
     """
     Factory function to create face detectors.
 
@@ -88,18 +89,15 @@ def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
     """
     method = method.lower()
 
-    if method == 'retinaface':
+    if method == "retinaface":
         return RetinaFace(**kwargs)
 
-    elif method == 'scrfd':
+    elif method == "scrfd":
         return SCRFD(**kwargs)
 
     else:
-        available_methods = ['retinaface', 'scrfd']
-        raise ValueError(
-            f"Unsupported detection method: '{method}'. "
-            f"Available methods: {available_methods}"
-        )
+        available_methods = ["retinaface", "scrfd"]
+        raise ValueError(f"Unsupported detection method: '{method}'. Available methods: {available_methods}")
 
 
 def list_available_detectors() -> Dict[str, Dict[str, Any]]:
@@ -110,36 +108,36 @@ def list_available_detectors() -> Dict[str, Dict[str, Any]]:
         Dict[str, Dict[str, Any]]: Dictionary of detector information
     """
     return {
-        'retinaface': {
-            'description': 'RetinaFace detector with high accuracy',
-            'supports_landmarks': True,
-            'paper': 'https://arxiv.org/abs/1905.00641',
-            'default_params': {
-                'model_name': 'mnet_v2',
-                'conf_thresh': 0.5,
-                'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
+        "retinaface": {
+            "description": "RetinaFace detector with high accuracy",
+            "supports_landmarks": True,
+            "paper": "https://arxiv.org/abs/1905.00641",
+            "default_params": {
+                "model_name": "mnet_v2",
+                "conf_thresh": 0.5,
+                "nms_thresh": 0.4,
+                "input_size": (640, 640),
+            },
+        },
+        "scrfd": {
+            "description": "SCRFD detector - fast and accurate with efficient architecture",
+            "supports_landmarks": True,
+            "paper": "https://arxiv.org/abs/2105.04714",
+            "default_params": {
+                "model_name": "scrfd_10g_kps",
+                "conf_thresh": 0.5,
+                "nms_thresh": 0.4,
+                "input_size": (640, 640),
+            },
         },
-        'scrfd': {
-            'description': 'SCRFD detector - fast and accurate with efficient architecture',
-            'supports_landmarks': True,
-            'paper': 'https://arxiv.org/abs/2105.04714',
-            'default_params': {
-                'model_name': 'scrfd_10g_kps',
-                'conf_thresh': 0.5,
-                'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
-        }
     }
 
 
 __all__ = [
-    'detect_faces',
-    'create_detector',
-    'list_available_detectors',
-    'SCRFD',
-    'RetinaFace',
-    'BaseDetector',
+    "detect_faces",
+    "create_detector",
+    "list_available_detectors",
+    "SCRFD",
+    "RetinaFace",
+    "BaseDetector",
 ]

uniface/detection/base.py

@@ -6,9 +6,10 @@
 Base classes for face detection.
 """
 
-import numpy as np
 from abc import ABC, abstractmethod
-from typing import Tuple, Dict, Any
+from typing import Any, Dict, Tuple
+
+import numpy as np
 
 
 class BaseDetector(ABC):
@@ -84,7 +85,7 @@ class BaseDetector(ABC):
         Returns:
             bool: True if landmarks are supported, False otherwise
         """
-        return hasattr(self, '_supports_landmarks') and self._supports_landmarks
+        return hasattr(self, "_supports_landmarks") and self._supports_landmarks
 
     def get_info(self) -> Dict[str, Any]:
         """
@@ -94,7 +95,7 @@ class BaseDetector(ABC):
             Dict[str, Any]: Detector information
         """
         return {
-            'name': self.__class__.__name__,
-            'supports_landmarks': self._supports_landmarks,
-            'config': self.config
+            "name": self.__class__.__name__,
+            "supports_landmarks": self._supports_landmarks,
+            "config": self.config,
         }

uniface/detection/retinaface.py

@@ -2,22 +2,22 @@
 # 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.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 (
+    decode_boxes,
+    decode_landmarks,
+    generate_anchors,
     non_max_supression,
     resize_image,
-    decode_boxes,
-    generate_anchors,
-    decode_landmarks
 )
 
 
@@ -59,13 +59,13 @@ class RetinaFace(BaseDetector):
         super().__init__(**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.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))
+        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.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}, "
@@ -133,7 +133,7 @@ class RetinaFace(BaseDetector):
         image: np.ndarray,
         max_num: int = 0,
         metric: Literal["default", "max"] = "max",
-        center_weight: float = 2.0
+        center_weight: float = 2.0,
     ) -> List[Dict[str, Any]]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
@@ -178,14 +178,16 @@ 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
-            if metric == 'max':
+            if metric == "max":
                 scores = areas
             else:
                 scores = areas - offset_dist_squared * center_weight
@@ -199,15 +201,17 @@ 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].astype(float).tolist(),
+                "confidence": detections[i, 4].item(),
+                "landmarks": landmarks[i].astype(float).tolist(),
             }
             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 +230,11 @@ 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)
@@ -242,7 +250,7 @@ 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
@@ -251,13 +259,22 @@ class RetinaFace(BaseDetector):
         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)
 
         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
@@ -276,12 +293,13 @@ def draw_bbox(frame, bbox, score, color=(0, 255, 0), thickness=2):
 
 
 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__":
     import cv2
+
     detector = RetinaFace(model_name=RetinaFaceWeights.MNET_050)
     print(detector.get_info())
     cap = cv2.VideoCapture(0)
@@ -304,9 +322,9 @@ 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)
@@ -318,8 +336,15 @@ 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"):

uniface/detection/scrfd.py

@@ -173,7 +173,11 @@ 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,
     ) -> List[Dict[str, Any]]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
@@ -311,7 +315,15 @@ 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"):

uniface/detection/utils.py

@@ -2,12 +2,12 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import cv2
-import math
 import itertools
-import numpy as np
+import math
+from typing import List, Tuple
 
-from typing import Tuple, List
+import cv2
+import numpy as np
 
 
 def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
@@ -59,12 +59,7 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
     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]

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, Union
 
-
-__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)
@@ -18,9 +23,9 @@ 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,
 )
 
 
@@ -72,7 +77,11 @@ def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]]
     return matrix, inverse_matrix
 
 
-def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: Union[int, Tuple[int, 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.
 

uniface/landmark/__init__.py

@@ -2,11 +2,11 @@
 # 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:
+def create_landmarker(method: str = "2d106det", **kwargs) -> BaseLandmarker:
     """
     Factory function to create facial landmark predictors.
 
@@ -18,15 +18,11 @@ def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
         Initialized landmarker instance.
     """
     method = method.lower()
-    if method == '2d106det':
+    if method == "2d106det":
         return Landmark106(**kwargs)
     else:
-        available = ['2d106det']
+        available = ["2d106det"]
         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__ = ["Landmark"]
 
 
 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
@@ -83,7 +83,7 @@ class Landmark106(BaseLandmarker):
 
         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)
@@ -149,14 +152,11 @@ 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
@@ -183,21 +183,21 @@ if __name__ == "__main__":
 
         if not faces:
             cv2.imshow("Facial Landmark Detection", frame)
-            if cv2.waitKey(1) & 0xFF == ord('q'):
+            if cv2.waitKey(1) & 0xFF == ord("q"):
                 break
             continue
 
         # 3. Loop through the list of face dictionaries
         for face in faces:
             # Extract the bounding box
-            bbox = face['bbox']
+            bbox = face["bbox"]
 
             # 4. Get landmarks for the current face using its bounding box
             landmarks = landmarker.get_landmarks(frame, bbox)
 
             # --- 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
@@ -205,7 +205,7 @@ if __name__ == "__main__":
             cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
 
         cv2.imshow("Facial Landmark Detection", frame)
-        if cv2.waitKey(1) & 0xFF == ord('q'):
+        if cv2.waitKey(1) & 0xFF == ord("q"):
             break
 
     cap.release()

uniface/log.py

@@ -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

@@ -2,19 +2,19 @@
 # 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"]
 
 
-__all__ = ['verify_model_weights']
-
-
-def verify_model_weights(model_name: str, root: str = '~/.uniface/models') -> str:
+def verify_model_weights(model_name: str, root: str = "~/.uniface/models") -> str:
     """
     Ensure model weights are present, downloading and verifying them using SHA-256 if necessary.
 
@@ -53,7 +53,7 @@ def verify_model_weights(model_name: str, root: str = '~/.uniface/models') -> st
         raise ValueError(f"No URL found for model '{model_name}'")
 
     file_ext = os.path.splitext(url)[1]
-    model_path = os.path.normpath(os.path.join(root, f'{model_name.value}{file_ext}'))
+    model_path = os.path.normpath(os.path.join(root, f"{model_name.value}{file_ext}"))
 
     if not os.path.exists(model_path):
         Logger.info(f"Downloading model '{model_name}' from {url}")
@@ -62,7 +62,7 @@ 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):
@@ -78,18 +78,21 @@ 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:

uniface/onnx_utils.py

@@ -77,10 +77,25 @@ 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}")
+
+        # 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)
+        print(f"Model loaded ({provider_display})")
+
         return session
     except Exception as e:
         Logger.error(f"Failed to create ONNX session: {e}", exc_info=True)

uniface/recognition/__init__.py

@@ -2,12 +2,12 @@
 # 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
 
-def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
+from .base import BaseRecognizer
+from .models import ArcFace, MobileFace, SphereFace
+
+
+def create_recognizer(method: str = "arcface", **kwargs) -> BaseRecognizer:
     """
     Factory function to create face recognizers.
 
@@ -44,20 +44,21 @@ def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
     """
     method = method.lower()
 
-    if method == 'arcface':
+    if method == "arcface":
         return ArcFace(**kwargs)
-    elif method == 'mobileface':
+    elif method == "mobileface":
         return MobileFace(**kwargs)
-    elif method == 'sphereface':
+    elif method == "sphereface":
         return SphereFace(**kwargs)
     else:
-        available = ['arcface', 'mobileface', 'sphereface']
+        available = ["arcface", "mobileface", "sphereface"]
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
+
 __all__ = [
     "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:
         """
@@ -73,7 +76,10 @@ class BaseRecognizer(ABC):
             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
@@ -104,7 +111,7 @@ 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

uniface/recognition/models.py

@@ -6,6 +6,7 @@ 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"]
@@ -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

@@ -2,9 +2,10 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from typing import List, Union
+
 import cv2
 import numpy as np
-from typing import List, Union
 
 
 def draw_detections(
@@ -12,7 +13,7 @@ def draw_detections(
     bboxes: Union[np.ndarray, List[List[float]]],
     scores: Union[np.ndarray, List[float]],
     landmarks: Union[np.ndarray, List[List[List[float]]]],
-    vis_threshold: float = 0.6
+    vis_threshold: float = 0.6,
 ):
     """
     Draws bounding boxes, scores, and landmarks from separate lists onto an image.
@@ -42,8 +43,15 @@ def draw_detections(
         cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 0, 255), thickness)
 
         # Draw score
-        cv2.putText(image, f"{score:.2f}", (bbox[0], bbox[1] - 10),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), thickness)
+        cv2.putText(
+            image,
+            f"{score:.2f}",
+            (bbox[0], bbox[1] - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            thickness,
+        )
 
         # Draw landmarks
         for j, point in enumerate(landmark_set):