DayBreak-u / Yolo Face With Landmark
yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测(包含关键点)
Stars: ✭ 180
Labels
Projects that are alternatives of or similar to Yolo Face With Landmark
GodlyTorch
[NOT MAINTAINED] An app that can control the intensity of the torch of your rooted android device.
Stars: ✭ 16 (-91.11%)
Mutual labels: light, torch
Winhue
Controlling the Philips Hue lighting system from your Windows PC.
Stars: ✭ 167 (-7.22%)
Mutual labels: light
Torch Dct
DCT (discrete cosine transform) functions for pytorch
Stars: ✭ 173 (-3.89%)
Mutual labels: torch
Facenet Pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Stars: ✭ 2,564 (+1324.44%)
Mutual labels: face-detection
Typora Misty Theme
Yet another elegant Typora theme designed with aesthetics in mind.
Stars: ✭ 179 (-0.56%)
Mutual labels: light
Attendance Using Face
Face-recognition using Siamese network
Stars: ✭ 174 (-3.33%)
Mutual labels: face-detection
Human
Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking and Age & Gender Prediction
Stars: ✭ 172 (-4.44%)
Mutual labels: face-detection
Slimsocial For Facebook
Light version of Facebook. Light both in the weight and in the use.
Stars: ✭ 171 (-5%)
Mutual labels: light
Face Api.js
JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js
Stars: ✭ 13,258 (+7265.56%)
Mutual labels: face-detection
Snapshotensemble
Snapshot Ensembles in Torch (Snapshot Ensembles: Train 1, Get M for Free)
Stars: ✭ 173 (-3.89%)
Mutual labels: torch
Semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
Stars: ✭ 170 (-5.56%)
Mutual labels: torch
Retinaface Tf2
RetinaFace (RetinaFace: Single-stage Dense Face Localisation in the Wild, published in 2019) reimplemented in Tensorflow 2.0, with pretrained weights available !
Stars: ✭ 176 (-2.22%)
Mutual labels: face-detection
Wechat Miniprogram Webar
A WeChat MiniProgram Image AR using computer vision. No OpenCV, No Deep Learning. Only JavaScript Implementation.
Stars: ✭ 163 (-9.44%)
Mutual labels: face-detection
Retinaface Tf2
RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
Stars: ✭ 178 (-1.11%)
Mutual labels: face-detection
yolo-face-with-landmark
实现的功能
- 添加关键点检测分支,使用wing loss
Installation
Clone and install
- git clone https://github.com/ouyanghuiyu/yolo-face-with-landmark
- 使用src/retinaface2yololandmark.py脚本将retinaface的标记文件转为yolo的格式使用,
- 使用src/create_train.py 创建训练样本
训练
python train.py --net mbv3_large_75 --backbone_weights \
./pretrained/mobilenetv3-large-0.75-9632d2a8.pth --batch-size 16
测试
python evaluation_on_widerface.py
cd widerface_evaluate
python evaluation.py
demo
python demo.py
精度
Widerface测试
- 在wider face val精度(单尺度输入分辨率:320*240)
方法 | Easy | Medium | Hard | Flops |
---|---|---|---|---|
Retinaface-Mobilenet-0.25(Mxnet) | 0.745 | 0.553 | 0.232 | |
mbv3large_1.0_yolov3(our) | 0.861 | 0.781 | 0.387 | 405M |
mbv3large_1.0_yolov3_light(our) | 0.856 | 0.770 | 0.370 | 311M |
mbv3large_0.75_yolov3(our) | 0.853 | 0.778 | 0.382 | 334M |
mbv3large_0.75_yolov3_light(our) | 0.845 | 0.766 | 0.365 | 240M |
mbv3samll_1.0_yolov3(our) | 0.798 | 0.696 | 0.3 | 185M |
mbv3small_1.0_yolov3_light(our) | 0.759 | 0.662 | 0.300 | 91M |
mbv3samll_0.75_yolov3(our) | 0.768 | 0.673 | 0.305 | 174M |
mbv3small_0.75_yolov3_light(our) | 0.754 | 0.647 | 0.291 | 80M |
- 在wider face val精度(单尺度输入分辨率:640*480)
方法 | Easy | Medium | Hard |
---|---|---|---|
Retinaface-Mobilenet-0.25(mxnet) | 0.879 | 0.807 | 0.481 |
mbv3large_1.0_yolov3(our) | 0.900 | 0.882 | 0.707 |
mbv3large_1.0_yolov3_light(our) | 0.900 | 0.874 | 0.683 |
mbv3large_0.75_yolov3(our) | 0.886 | 0.871 | 0.694 |
mbv3large_0.75_yolov3_light(our) | 0.881 | 0.862 | 0.678 |
mbv3samll_1.0_yolov3(our) | 0.856 | 0.827 | 0.602 |
mbv3small_1.0_yolov3_light(our) | 0.847 | 0.807 | 0.578 |
mbv3samll_0.75_yolov3(our) | 0.841 | 0.815 | 0.584 |
mbv3small_0.75_yolov3_light(our) | 0.832 | 0.796 | 0.553 |
ps: 测试的时候,长边为320 或者 640 ,图像等比例缩放
测试
References
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].