ZF/uniface
1
0
Fork 0
mirror of https://github.com/yakhyo/uniface.git synced 2025-12-30 09:02:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Change setup.py to pyproject.toml and remove torch dependency

Browse Source
This commit is contained in:
yakhyo
2025-03-16 14:36:35 +09:00
parent 4256407044
commit d586cffb3a
10 changed files with 111 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -70,7 +70,7 @@ from uniface import RetinaFace
# Initialize the RetinaFace model # Initialize the RetinaFace model
uniface_inference = RetinaFace( uniface_inference = RetinaFace(
model="retinaface_mnet_v2", # Model name model_name="retinaface_mnet_v2", # Model name
conf_thresh=0.5, # Confidence threshold conf_thresh=0.5, # Confidence threshold
pre_nms_topk=5000, # Pre-NMS Top-K detections pre_nms_topk=5000, # Pre-NMS Top-K detections
nms_thresh=0.4, # NMS IoU threshold nms_thresh=0.4, # NMS IoU threshold
@@ -169,7 +169,7 @@ cv2.destroyAllWindows()
from typings import Tuple from typings import Tuple
RetinaFace( RetinaFace(
model: str, model_name: str,
conf_thresh: float = 0.5, conf_thresh: float = 0.5,
pre_nms_topk: int = 5000, pre_nms_topk: int = 5000,
nms_thresh: float = 0.4, nms_thresh: float = 0.4,

24
examples/face_alignment.ipynb
View File

File diff suppressed because one or more lines are too long

20
examples/face_detection.ipynb
View File

@@ -63,20 +63,20 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"2025-01-09 05:10:37,310 - INFO - Initializing RetinaFace with model=retinaface_mnet_v2, conf_thresh=0.5, nms_thresh=0.4, pre_nms_topk=5000, post_nms_topk=750, dynamic_size=False, input_size=(640, 640)\n", "2025-03-16 14:32:33,786 - INFO - Initializing RetinaFace with model=retinaface_mnet_v2, conf_thresh=0.5, nms_thresh=0.4, pre_nms_topk=5000, post_nms_topk=750, dynamic_size=False, input_size=(640, 640)\n",
"2025-01-09 05:10:37,349 - INFO - Verified model weights located at: /home/yakhyo/.uniface/models/retinaface_mnet_v2.onnx\n", "2025-03-16 14:32:33,830 - INFO - Verified model weights located at: C:\\Users\\yakhyo/.uniface/models\\retinaface_mnet_v2.onnx\n",
"2025-01-09 05:10:37,445 - INFO - Successfully initialized the model from /home/yakhyo/.uniface/models/retinaface_mnet_v2.onnx\n" "2025-03-16 14:32:33,926 - INFO - Successfully initialized the model from C:\\Users\\yakhyo/.uniface/models\\retinaface_mnet_v2.onnx\n"
] ]
} }
], ],
"source": [ "source": [
"# Initialize the RetinaFace model\n", "# Initialize the RetinaFace model\n",
"uniface_inference = RetinaFace(\n", "uniface_inference = RetinaFace(\n",
" model=\"retinaface_mnet_v2\", # Model name\n", " model_name=\"retinaface_mnet_v2\", # Model name\n",
" conf_thresh=0.5, # Confidence threshold\n", " conf_thresh=0.5, # Confidence threshold\n",
" pre_nms_topk=5000, # Pre-NMS Top-K detections\n", " pre_nms_topk=5000, # Pre-NMS Top-K detections\n",
" nms_thresh=0.4, # NMS IoU threshold\n", " nms_thresh=0.4, # NMS IoU threshold\n",
" post_nms_topk=750 # Post-NMS Top-K detections,\n", " post_nms_topk=750 # Post-NMS Top-K detections,\n",
")" ")"
] ]
}, },
@@ -262,7 +262,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "face", "display_name": "torch",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@@ -276,7 +276,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.10" "version": "3.12.9"
} }
}, },
"nbformat": 4, "nbformat": 4,

35
pyproject.toml Normal file
View File

@@ -0,0 +1,35 @@
[project]
name = "uniface"
version = "0.1.7"
description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection"
readme = "README.md"
license = { text = "MIT" }
authors = [
{ name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }
]
dependencies = [
"numpy",
"opencv-python",
"onnx",
"onnxruntime-gpu",
"scikit-image",
"requests"
]
requires-python = ">=3.8"
[project.optional-dependencies]
dev = ["pytest"]
[project.urls]
Homepage = "https://github.com/yakhyo/uniface"
Repository = "https://github.com/yakhyo/uniface"
[build-system]
requires = ["setuptools>=64", "wheel"]
build-backend = "setuptools.build_meta"
[tool.setuptools]
packages = ["uniface"]
[tool.setuptools.package-data]
"uniface" = ["*.txt", "*.md"]

8
requirements.txt
View File

@@ -1,9 +1,7 @@
pytest
numpy numpy
opencv-python opencv-python
opencv-python-headless
onnx onnx
onnxruntime onnxruntime-gpu
scikit-image
requests requests
torch pytest
scikit-image

46
setup.py
View File

@@ -1,46 +0,0 @@
import os
from setuptools import setup, find_packages
# Read the README file for the long description
long_description = ""
if os.path.exists("README.md"):
with open("README.md", "r", encoding="utf-8") as f:
long_description = f.read()
setup(
name="uniface",
version="0.1.6",
packages=find_packages(),
install_requires=[
"numpy",
"opencv-python",
"onnx",
"onnxruntime",
"requests",
"torch",
"scikit-image"
],
extras_require={
"dev": ["pytest"],
},
description="UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection",
long_description=long_description,
long_description_content_type="text/markdown",
author="Yakhyokhuja Valikhujaev",
author_email="yakhyo9696@gmail.com",
url="https://github.com/yakhyo/uniface",
license="MIT",
classifiers=[
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Topic :: Software Development :: Libraries :: Python Modules",
],
keywords="face detection, face recognition, facial landmark, facial attribute, onnx, opencv, retinaface",
python_requires=">=3.8",
)

2
test.py
View File

@@ -39,7 +39,7 @@ if __name__ == '__main__':
# Initialize and run the ONNX inference # Initialize and run the ONNX inference
retinaface_inference = RetinaFace( retinaface_inference = RetinaFace(
model="retinaface_mnet_v2", model_name="retinaface_mnet_v2",
conf_thresh=0.5, conf_thresh=0.5,
pre_nms_topk=5000, pre_nms_topk=5000,
nms_thresh=0.4, nms_thresh=0.4,

2
uniface/__init__.py
View File

@@ -13,7 +13,7 @@
__license__ = "MIT" __license__ = "MIT"
__author__ = "Yakhyokhuja Valikhujaev" __author__ = "Yakhyokhuja Valikhujaev"
__version__ = "0.1.6" __version__ = "0.1.7"
from uniface.retinaface import RetinaFace from uniface.retinaface import RetinaFace

48
uniface/common.py
View File

@@ -7,7 +7,6 @@ import math
import itertools import itertools
import numpy as np import numpy as np
import torch
from typing import Tuple, List from typing import Tuple, List
@@ -44,7 +43,7 @@ def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.
return image, resize_factor return image, resize_factor
def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> torch.Tensor: def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
""" """
Generate anchor boxes for a given image size. Generate anchor boxes for a given image size.
@@ -52,7 +51,7 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> torch.Tensor:
image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640). image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640).
Returns: Returns:
torch.Tensor: Anchor box coordinates as a tensor. np.ndarray: Anchor box coordinates as a NumPy array.
""" """
image_size = image_size image_size = image_size
@@ -79,7 +78,7 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> torch.Tensor:
for cy, cx in itertools.product(dense_cy, dense_cx): for cy, cx in itertools.product(dense_cy, dense_cx):
anchors += [cx, cy, s_kx, s_ky] anchors += [cx, cy, s_kx, s_ky]
output = torch.Tensor(anchors).view(-1, 4) output = np.array(anchors, dtype=np.float32).reshape(-1, 4)
return output return output
@@ -123,56 +122,57 @@ def nms(dets: List[np.ndarray], threshold: float):
return keep return keep
def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> torch.Tensor: def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
""" """
Decode locations from predictions using priors to undo Decode locations from predictions using priors to undo
the encoding done for offset regression at train time. the encoding done for offset regression at train time.
Args: Args:
loc (tensor): Location predictions for loc layers, shape: [num_priors, 4] loc (np.ndarray): Location predictions for loc layers, shape: [num_priors, 4]
priors (tensor): Prior boxes in center-offset form, shape: [num_priors, 4] priors (np.ndarray): Prior boxes in center-offset form, shape: [num_priors, 4]
variances (list[float]): Variances of prior boxes variances (list[float]): Variances of prior boxes
Returns: Returns:
tensor: Decoded bounding box predictions np.ndarray: Decoded bounding box predictions
""" """
# Compute centers of predicted boxes # Compute centers of predicted boxes
cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:] cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:]
# Compute widths and heights of predicted boxes # Compute widths and heights of predicted boxes
wh = priors[:, 2:] * torch.exp(loc[:, 2:] * variances[1]) wh = priors[:, 2:] * np.exp(loc[:, 2:] * variances[1])
# Convert center, size to corner coordinates # Convert center, size to corner coordinates
boxes = torch.empty_like(loc) boxes = np.zeros_like(loc)
boxes[:, :2] = cxcy - wh / 2 # xmin, ymin boxes[:, :2] = cxcy - wh / 2 # xmin, ymin
boxes[:, 2:] = cxcy + wh / 2 # xmax, ymax boxes[:, 2:] = cxcy + wh / 2 # xmax, ymax
return boxes return boxes
def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> torch.Tensor: def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
""" """
Decode landmarks from predictions using prior boxes to reverse the encoding done during training. Decode landmark predictions using prior boxes.
Args: Args:
predictions (tensor): Landmark predictions for localization layers. predictions (np.ndarray): Landmark predictions, shape: [num_priors, 10]
Shape: [num_priors, 10] where each prior contains 5 landmark (x, y) pairs. priors (np.ndarray): Prior boxes, shape: [num_priors, 4]
priors (tensor): Prior boxes in center-offset form. variances (list): Scaling factors for landmark offsets.
Shape: [num_priors, 4], where each prior has (cx, cy, width, height).
variances (list[float]): Variances of the prior boxes to scale the decoded values.
Returns: Returns:
landmarks (tensor): Decoded landmark predictions. np.ndarray: Decoded landmarks, shape: [num_priors, 10]
Shape: [num_priors, 10] where each row contains the decoded (x, y) pairs for 5 landmarks.
""" """
# Reshape predictions to [num_priors, 5, 2] to handle each pair (x, y) in a batch # Reshape predictions to [num_priors, 5, 2] to process landmark points
predictions = predictions.view(predictions.size(0), 5, 2) predictions = predictions.reshape(predictions.shape[0], 5, 2)
# Perform the same operation on all landmark pairs at once # Expand priors to match (num_priors, 5, 2)
landmarks = priors[:, :2].unsqueeze(1) + predictions * variances[0] * priors[:, 2:].unsqueeze(1) priors_xy = np.repeat(priors[:, :2][:, np.newaxis, :], 5, axis=1) # (num_priors, 5, 2)
priors_wh = np.repeat(priors[:, 2:][:, np.newaxis, :], 5, axis=1) # (num_priors, 5, 2)
# Compute absolute landmark positions
landmarks = priors_xy + predictions * variances[0] * priors_wh
# Flatten back to [num_priors, 10] # Flatten back to [num_priors, 10]
landmarks = landmarks.view(landmarks.size(0), -1) landmarks = landmarks.reshape(landmarks.shape[0], -1)
return landmarks return landmarks

44
uniface/retinaface.py
View File

@@ -7,12 +7,10 @@ import cv2
import numpy as np import numpy as np
import onnxruntime as ort import onnxruntime as ort
import torch
from typing import Tuple, List, Optional, Literal from typing import Tuple, List, Optional, Literal
from uniface.log import Logger from uniface.log import Logger
from uniface.model_store import verify_model_weights from uniface.model_store import verify_model_weights
from uniface.common import ( from uniface.common import (
nms, nms,
resize_image, resize_image,
@@ -27,28 +25,32 @@ class RetinaFace:
A class for face detection using the RetinaFace model. A class for face detection using the RetinaFace model.
Args: Args:
model (str): Path or identifier of the model weights. model_name (str): Name of the model.
conf_thresh (float): Confidence threshold for detections. Defaults to 0.5. conf_thresh (float, optional): Confidence threshold for detections. Defaults to 0.5.
nms_thresh (float): Non-maximum suppression threshold. Defaults to 0.4. nms_thresh (float, optional): Non-maximum suppression (NMS) threshold. Defaults to 0.4.
pre_nms_topk (int): Maximum number of detections before NMS. Defaults to 5000. pre_nms_topk (int, optional): Maximum number of detections considered before applying NMS. Defaults to 5000.
post_nms_topk (int): Maximum number of detections after NMS. Defaults to 750. post_nms_topk (int, optional): Maximum number of detections retained after NMS. Defaults to 750.
dynamic_size (Optional[bool]): Whether to adjust anchor generation dynamically based on image size. Defaults to False. dynamic_size (bool, optional): Whether to dynamically adjust anchor generation based on image size. Defaults to False.
input_size (Optional[Tuple[int, int]]): Static input size for the model (width, height). Defaults to (640, 640). input_size (Tuple[int, int], optional): Static input size for the model (width, height). Used when `dynamic_size=False`. Defaults to (640, 640).
Attributes: Attributes:
conf_thresh (float): Confidence threshold for filtering detections. conf_thresh (float): Confidence threshold for filtering detections.
nms_thresh (float): Threshold for NMS to remove duplicate detections. nms_thresh (float): NMS threshold to remove duplicate detections.
pre_nms_topk (int): Maximum detections to consider before applying NMS. pre_nms_topk (int): Number of detections considered before applying NMS.
post_nms_topk (int): Maximum detections retained after applying NMS. post_nms_topk (int): Maximum number of detections retained after applying NMS.
dynamic_size (bool): Indicates if input size and anchors are dynamically adjusted. dynamic_size (bool): Whether the model dynamically adjusts input size and anchors.
input_size (Tuple[int, int]): The model's input image size. input_size (Tuple[int, int] or None): The model's fixed input size (if `dynamic_size=False`), otherwise None.
_model_path (str): Path to the model weights. _model_path (str): Verified path to the model weights.
_priors (torch.Tensor): Precomputed anchor boxes for static input size. _priors (np.ndarray or None): Precomputed anchor boxes when using static input size. None if `dynamic_size=True`.
Raises:
ValueError: If the model weights cannot be found or verified.
RuntimeError: If there is an error initializing the model.
""" """
def __init__( def __init__(
self, self,
model: str, model_name: str,
conf_thresh: float = 0.5, conf_thresh: float = 0.5,
nms_thresh: float = 0.4, nms_thresh: float = 0.4,
pre_nms_topk: int = 5000, pre_nms_topk: int = 5000,
@@ -65,13 +67,13 @@ class RetinaFace:
self.input_size = input_size self.input_size = input_size
Logger.info( Logger.info(
f"Initializing RetinaFace with model={model}, conf_thresh={conf_thresh}, nms_thresh={nms_thresh}, " f"Initializing RetinaFace with model={model_name}, conf_thresh={conf_thresh}, nms_thresh={nms_thresh}, "
f"pre_nms_topk={pre_nms_topk}, post_nms_topk={post_nms_topk}, dynamic_size={dynamic_size}, " f"pre_nms_topk={pre_nms_topk}, post_nms_topk={post_nms_topk}, dynamic_size={dynamic_size}, "
f"input_size={input_size}" f"input_size={input_size}"
) )
# Get path to model weights # Get path to model weights
self._model_path = verify_model_weights(model) self._model_path = verify_model_weights(model_name)
Logger.info(f"Verified model weights located at: {self._model_path}") Logger.info(f"Verified model weights located at: {self._model_path}")
# Precompute anchors if using static size # Precompute anchors if using static size
@@ -217,8 +219,8 @@ class RetinaFace:
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 # Decode boxes and landmarks
boxes = decode_boxes(torch.tensor(loc), self._priors).cpu().numpy() boxes = decode_boxes(loc, self._priors)
landmarks = decode_landmarks(torch.tensor(landmarks), self._priors).cpu().numpy() landmarks = decode_landmarks(landmarks, self._priors)
boxes, landmarks = self._scale_detections(boxes, landmarks, resize_factor, shape=(shape[0], shape[1])) boxes, landmarks = self._scale_detections(boxes, landmarks, resize_factor, shape=(shape[0], shape[1]))