https://github.com/jianzhnie/dsfd_pytorch
pytorch 实现的DSFD， 更高效更简洁
https://github.com/jianzhnie/dsfd_pytorch
dsfd facedetection resnet vgg16
Last synced: about 1 month ago
JSON representation
pytorch 实现的DSFD， 更高效更简洁
- Host: GitHub
- URL: https://github.com/jianzhnie/dsfd_pytorch
- Owner: jianzhnie
- Created: 2019-11-19T12:52:20.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-11-19T14:48:03.000Z (almost 6 years ago)
- Last Synced: 2024-12-29T13:44:56.398Z (10 months ago)
- Topics: dsfd, facedetection, resnet, vgg16
- Language: Python
- Size: 73.5 MB
- Stars: 6
- Watchers: 4
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## DSFD: Dual Shot Face Detector ##
[A PyTorch Implementation of Dual Shot Face Detector](https://arxiv.org/abs/1810.10220?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+arxiv%2FQSXk+%28ExcitingAds%21+cs+updates+on+arXiv.org%29)
### Description
I use basenet [vgg](https://pan.baidu.com/s/1Q-YqoxJyqvln6KTcIck1tQ) to train DSFD,the model can be downloaded in [DSFD](https://pan.baidu.com/s/17cpDHEwYVxWmOIPqUy5zCQ).the AP in WIDER FACE as following:
| Easy MAP | Medium MAP | hard MAP |
| ---------|------------| --------- |
| 0.946 | 0.937 | 0.880 |
the AP in AFW,PASCAL,FDDB as following:
| AFW | PASCAL | FDDB |
| --------- |-----------| ---------|
| 99.89 | 99.11 | 0.983 |
I'm using resnet50/resnet101 to train DSFD,the result will be published later on
### Requirement
* pytorch 1.3
* opencv
* numpy
* easydict
### Prepare data
1. download WIDER face dataset
2. modify data/config.py
3. ``` python prepare_wider_data.py```
### Train
```
python main.py --batch_size 4
--model vgg\resnet50\resnet101
--lr 5e-4
```
### Evalution
according to yourself dataset path,modify data/config.py
1. Evaluate on AFW.
```
python tools/afw_test.py
```
2. Evaluate on FDDB
```
python tools/fddb_test.py
```
3. Evaluate on PASCAL face
```
python tools/pascal_test.py
```
4. test on WIDER FACE
```
python tools/wider_test.py
```
### Demo
you can test yourself image
```
python demo.py
```
### Result
1. demo
### References
* [Dual Shot Face Detector](https://arxiv.org/abs/1810.10220?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+arxiv%2FQSXk+%28ExcitingAds%21+cs+updates+on+arXiv.org%29)
* [ssd.pytorch](https://github.com/amdegroot/ssd.pytorch)
* [S3FD_pytorch](https://github.com/jianzhnie/S3FD_pytorch)
* [FaceDetection-DSFD](https://github.com/TencentYoutuResearch/FaceDetection-DSFD)