2024.04 ncnn-android-yolov8-face
2023.04 yolov8-face (🔥🔥🔥↑)
2022.10 yolov7-face (🔥🔥🔥↑)
2022.8: yolov7
| Method | Test Size | Easy | Medium | Hard | FLOPs (B) @640 |
|---|---|---|---|---|---|
| yolov7-lite-t | 640 | 88.7 | 85.2 | 71.5 | 0.8 |
| yolov7-lite-s | 640 | 92.7 | 89.9 | 78.5 | 3.0 |
| yolov7-tiny | 640 | 94.7 | 92.6 | 82.1 | 13.2 |
| yolov7s | 640 | 94.8 | 93.1 | 85.2 | 16.8 |
| yolov7 | 640 | 96.9 | 95.5 | 88.0 | 103.4 |
| yolov7+TTA | 640 | 97.2 | 95.8 | 87.7 | 103.4 |
2021.12: Yolov5-face to TensorRT.
| Backbone | Pytorch(ms) | TensorRT_FP16(ms) |
|---|---|---|
| yolov5n-0.5 | 7.7 | 2.1 |
| yolov5n-face | 7.7 | 2.4 |
| yolov5s-face | 5.6 | 2.2 |
| yolov5m-face | 9.9 | 3.3 |
| yolov5l-face | 15.9 | 4.5 |
Pytorch=1.10.0+cu102 TensorRT=8.2.0.6 Hardware=rtx2080ti
2021.11: BlazeFace
| Method | multi scale | Easy | Medium | Hard | Model Size(MB) | Link |
|---|---|---|---|---|---|---|
| BlazeFace | Ture | 88.5 | 85.5 | 73.1 | 0.472 | https://github.com/PaddlePaddle/PaddleDetection |
| BlazeFace-FPN-SSH | Ture | 90.7 | 88.3 | 79.3 | 0.479 | https://github.com/PaddlePaddle/PaddleDetection |
| yolov5-blazeface | True | 90.4 | 88.7 | 78.0 | 0.493 | https://pan.baidu.com/s/1RHp8wa615OuDVhsO-qrMpQ pwd:r3v3 https://drive.google.com/file/d/1adi6ke2vCLQFcpbvFqWo_J4wZIfPqSMG |
| yolov5-blazeface-fpn | True | 90.8 | 89.4 | 79.1 | 0.493 | - |
2021.08: Add new training dataset Multi-Task-Facial,improve large face detection.
| Method | Easy | Medium | Hard |
|---|---|---|---|
| YOLOv5s | 94.56 | 92.92 | 83.84 |
| YOLOv5m | 95.46 | 93.87 | 85.54 |
QQ Group: 1164802745
Yolov5-face is a real-time,high accuracy face detection.
Single Scale Inference on VGA resolution（max side is equal to 640 and scale).
Large family
| Method | Backbone | Easy | Medium | Hard | #Params(M) | #Flops(G) |
|---|---|---|---|---|---|---|
| DSFD (CVPR19) | ResNet152 | 94.29 | 91.47 | 71.39 | 120.06 | 259.55 |
| RetinaFace (CVPR20) | ResNet50 | 94.92 | 91.90 | 64.17 | 29.50 | 37.59 |
| HAMBox (CVPR20) | ResNet50 | 95.27 | 93.76 | 76.75 | 30.24 | 43.28 |
| TinaFace (Arxiv20) | ResNet50 | 95.61 | 94.25 | 81.43 | 37.98 | 172.95 |
| SCRFD-34GF(Arxiv21) | Bottleneck Res | 96.06 | 94.92 | 85.29 | 9.80 | 34.13 |
| SCRFD-10GF(Arxiv21) | Basic Res | 95.16 | 93.87 | 83.05 | 3.86 | 9.98 |
| - | - | - | - | - | - | - |
| YOLOv5s | CSPNet | 94.67 | 92.75 | 83.03 | 7.075 | 5.751 |
| YOLOv5s6 | CSPNet | 95.48 | 93.66 | 82.8 | 12.386 | 6.280 |
| YOLOv5m | CSPNet | 95.30 | 93.76 | 85.28 | 21.063 | 18.146 |
| YOLOv5m6 | CSPNet | 95.66 | 94.1 | 85.2 | 35.485 | 19.773 |
| YOLOv5l | CSPNet | 95.78 | 94.30 | 86.13 | 46.627 | 41.607 |
| YOLOv5l6 | CSPNet | 96.38 | 94.90 | 85.88 | 76.674 | 45.279 |
Small family
| Method | Backbone | Easy | Medium | Hard | #Params(M) | #Flops(G) |
|---|---|---|---|---|---|---|
| RetinaFace (CVPR20 | MobileNet0.25 | 87.78 | 81.16 | 47.32 | 0.44 | 0.802 |
| FaceBoxes (IJCB17) | 76.17 | 57.17 | 24.18 | 1.01 | 0.275 | |
| SCRFD-0.5GF(Arxiv21) | Depth-wise Conv | 90.57 | 88.12 | 68.51 | 0.57 | 0.508 |
| SCRFD-2.5GF(Arxiv21) | Basic Res | 93.78 | 92.16 | 77.87 | 0.67 | 2.53 |
| - | - | - | - | - | - | - |
| YOLOv5n | ShuffleNetv2 | 93.74 | 91.54 | 80.32 | 1.726 | 2.111 |
| YOLOv5n-0.5 | ShuffleNetv2 | 90.76 | 88.12 | 73.82 | 0.447 | 0.571 |
- Download WIDERFace datasets.
- Download annotation files from google drive.
cd data
python3 train2yolo.py /path/to/original/widerface/train [/path/to/save/widerface/train]
python3 val2yolo.py /path/to/original/widerface [/path/to/save/widerface/val]CUDA_VISIBLE_DEVICES="0,1,2,3" python3 train.py --data data/widerface.yaml --cfg models/yolov5s.yaml --weights 'pretrained models'python3 test_widerface.py --weights 'your test model' --img-size 640
cd widerface_evaluate
python3 evaluation.py
First row: RetinaFace, 2nd row: YOLOv5m-Face
YOLO5Face was used in the 3rd place standard face recogntion track of the ICCV2021 Masked Face Recognition Challenge.
https://github.com/ultralytics/yolov5
https://github.com/biubug6/Pytorch_Retinaface
https://github.com/deepinsight/insightface
-
If you think this work is useful for you, please cite
@article{YOLO5Face, title = {YOLO5Face: Why Reinventing a Face Detector}, author = {Delong Qi and Weijun Tan and Qi Yao and Jingfeng Liu}, booktitle = {ArXiv preprint ArXiv:2105.12931}, year = {2021} }