Packaged version YOLOv5 Face Detector
Project description
Yolov5 Face Detection
Description
The project is a wrap over yolov5-face repo. Made simple portable interface for model import and inference. Model detects faces on images and returns bounding boxes and coordinates of 5 facial keypoints, which can be used for face alignment.
Installation
pip install yolov5facedetector
Usage example
from yolov5facedetector.face_detector import YoloDetector
import numpy as np
from PIL import Image
model = YoloDetector(target_size=720,gpu=0,min_face=90)
rgb_array_img = np.array(Image.open('test_image.jpg')) # Will make RGB Numpy Array Image
bboxes, confs, points = model.predict(rgb_array_img)
You can also pass several images packed in a list to get multi-image predictions.
bboxes, confs, points = model.predict([image1,image2])
Other pretrained models
Currently Support YOLOv5 type n,m & l type of model from yolov5-face repo. Default model type is 'yolov5n' but you can change to m & l (larger model version) which is auto download when first time used
Example below:
model = YoloFace(yolo_type='yolov5l',target_size=720) # Will download weight file automatically
bboxes, confs, points = model.predict(rgb_array_img)
Result example
Citiation
Thanks to deepcam-cn for pretrained models and Rebrikov Artem for providing wrapper function of YOLOv5Face.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for yolov5facedetector-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7b72fc579b8a1f40b8a64668a8c03bc07365c86c918db12459cc1c6bda37dd88 |
|
MD5 | cff74e233f232caf81c77f11944d062f |
|
BLAKE2b-256 | a1962769095ed7285039671223652fc8a1af849651eaf45b88886417e35466cc |