# CenterFace.pytorch

**Repository Path**: hchouse/CenterFace.pytorch

## Basic Information

- **Project Name**: CenterFace.pytorch
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-05-30
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# the real-time face detection Centerface

unofficial version of centerface, which achieves the best balance between speed and accuracy. Centerface is a practical anchor-free face detection and alignment method for edge devices.

The project provides training scripts, training data sets, and pre-training models to facilitate users to reproduce the results. Finally, thank the centerface's author for the training advice.


## performance results on the validation set of WIDER_FACE 
use the same train dataset without additional data  
for multi-scale,set the scale with **0.8,1.0,1.2,1.4**, but they also resize to 800*800, so i think it not the real multi-scale test.


| Method | Easy | Medium | Hard|
|:--------:| :--------:| :---------:| :------:|
| ours(one scale)| 0.9206 | 0.9089   | 0.7846
| original | 0.922 | 0.911 | 0.782 |
| ours(multi-scale) | 0.9306 | 0.9193 | 0.8008 |


## Requirements
use pytorch, you can use pip or conda to install the requirements
```sybase
# for pip
cd $project
pip install -r requirements.txt

# for conda
conda env create -f enviroment.yaml
```

## Test
1. download the pretrained model from [Baidu](https://pan.baidu.com/s/1sU3pRBTFebbsMDac-1HsQA) password: etdi

2. download the validation set of [WIDER_FACE](https://pan.baidu.com/s/1b5Uku0Bb13Zk9mf7mkZ3FA) password:  y4wg
3. test on the validation set
```sybase
cd $project/src
source activate torch110
python test_wider_face.py
```

4. calculate the accuracy
```sybase
cd $project/evaluate
python3 setup.py build_ext --inplace
python evaluation.py --pred {the result folder}
    
>>>
Easy   Val AP: 0.9257383419951156
Medium Val AP: 0.9131308732465665
Hard   Val AP: 0.7717305552550734
```

5. result  
![result](./readme/000388_result.png)

6. face recognition video  
[video](https://www.bilibili.com/video/av91632471/)

## Train
the backbone use mobilev2 as the same with the original paper
The annotation file is in coco format. the annotation file and train data can download for [Baidu](https://pan.baidu.com/s/1j_2wggZ3bvCuOAfZvjWqTg) password:  f9hh  
train
```sybase
cd $project/src/tools
source activate torch110
python main.py
```

## the train tricks
Training directly with the current code will not achieve the precision of the paper (I have also tested various scenarios).

Here's how I train:

1. First train with the size of 640×640/514×514

2. Then fine tune with the size of 800×800

3. For the easy and hard part, s = s * np.random. Choice (np.arange(0.3, 1.2, 0.1)). The larger the value, the more small samples will be generated

or you can fine tuning on the pretrained model.

---

## Train on your own data
follow the [CenterNet](https://github.com/xingyizhou/CenterNet)

---

## TO DO
- [ ] use more powerful and small backbone
- [ ] use other FPN tricks



## reference
borrow code from [CenterNet](https://github.com/xingyizhou/CenterNet)
> [**CenterNet**](https://github.com/xingyizhou/CenterNet)  
> [CenterMulti](https://github.com/bleakie/CenterMulti)  
> [Star-Clouds/CenterFace](https://github.com/Star-Clouds/CenterFace)