https://github.com/jianzhnie/s3fd_pytorch
pytorch 实现的S3FD，对原来的代码进行了优化，更简洁高效
https://github.com/jianzhnie/s3fd_pytorch
facedetection s3fd ssd
Last synced: about 1 month ago
JSON representation
pytorch 实现的S3FD，对原来的代码进行了优化，更简洁高效
- Host: GitHub
- URL: https://github.com/jianzhnie/s3fd_pytorch
- Owner: jianzhnie
- Created: 2019-11-18T07:55:15.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-10-14T13:17:03.000Z (almost 4 years ago)
- Last Synced: 2025-04-03T07:51:23.086Z (6 months ago)
- Topics: facedetection, s3fd, ssd
- Language: Python
- Size: 75 MB
- Stars: 8
- Watchers: 3
- Forks: 1
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## S³FD: Single Shot Scale-invariant Face Detector ##
A PyTorch Implementation of Single Shot Scale-invariant Face Detector
### Description
Meanwhile train hand and head with S3FD,hand dataset is [Egohands Dataset](http://vision.soic.indiana.edu/projects/egohands/),head dataset is [SCUT-HEAD](https://github.com/HCIILAB/SCUT-HEAD-Dataset-Release),we can download [hand model](https://pan.baidu.com/s/1_d4HqioBJknGj2ypwtYaXg) and [face model](https://pan.baidu.com/s/1epyTAUc6qSt3oZ7veK4oEw)
### Requirement
* pytorch 1.3.0
* opencv
* numpy
* easydict
### Prepare data
1. download WIDER face dataset、Egohands dataset and SCUT-HEAD
2. modify data/config.py
3. ``` python prepare_wider_data.py ```
### Train
We can choose different dataset to train different target[face,head,hand]
```
python main.py --batch_size 4 --dataset face\hand\head
```
### Evalution
according to yourself dataset path,modify data/config.py
1. Evaluate on AFW.
```
python afw_test.py
```
2. Evaluate on FDDB
```
python fddb_test.py
```
3. Evaluate on PASCAL face
```
python pascal_test.py
```
4. test on WIDER FACE
```
python wider_test.py
```
### Demo
you can test yourself image
```
python demo.py
```
### Result
1. AFW PASCAL FDDB
AFW AP=99.81 paper=99.85
PASCAL AP=98.77 paper=98.49
FDDB AP=0.975 paper=0.983
WIDER FACE:
Easy AP=0.925 paper = 0.927
Medium AP=0.925 paper = 0.924
Hard AP=0.854 paper = 0.852
2. demo
### References
* [S³FD: Single Shot Scale-invariant Face Detector](https://arxiv.org/abs/1708.05237)
* [ssd.pytorch](https://github.com/amdegroot/ssd.pytorch)