Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/biubug6/Pytorch_Retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.
https://github.com/biubug6/Pytorch_Retinaface

Last synced: about 1 month ago
JSON representation

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Lists

README 

        
# RetinaFace in PyTorch



A [PyTorch](https://pytorch.org/) implementation of [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://arxiv.org/abs/1905.00641). Model size only 1.7M, when Retinaface use mobilenet0.25 as backbone net. We also provide resnet50 as backbone net to get better result. The official code in Mxnet can be found [here](https://github.com/deepinsight/insightface/tree/master/RetinaFace).



## Mobile or Edge device deploy

We also provide a set of Face Detector for edge device in [here](https://github.com/biubug6/Face-Detector-1MB-with-landmark) from python training to C++ inference.



## WiderFace Val Performance in single scale When using Resnet50 as backbone net.

| Style | easy | medium | hard |

|:-|:-:|:-:|:-:|

| Pytorch (same parameter with Mxnet) | 94.82 % | 93.84% | 89.60% |

| Pytorch (original image scale) | 95.48% | 94.04% | 84.43% |

| Mxnet | 94.86% | 93.87% | 88.33% |

| Mxnet(original image scale) | 94.97% | 93.89% | 82.27% |



## WiderFace Val Performance in single scale When using Mobilenet0.25 as backbone net.

| Style | easy | medium | hard |

|:-|:-:|:-:|:-:|

| Pytorch (same parameter with Mxnet) | 88.67% | 87.09% | 80.99% |

| Pytorch (original image scale) | 90.70% | 88.16% | 73.82% |

| Mxnet | 88.72% | 86.97% | 79.19% |

| Mxnet(original image scale) | 89.58% | 87.11% | 69.12% |




## FDDB Performance.

| FDDB(pytorch) | performance |

|:-|:-:|

| Mobilenet0.25 | 98.64% |

| Resnet50 | 99.22% |




### Contents

- [Installation](#installation)

- [Training](#training)

- [Evaluation](#evaluation)

- [TensorRT](#tensorrt)

- [References](#references)



## Installation

##### Clone and install

1. git clone https://github.com/biubug6/Pytorch_Retinaface.git



2. Pytorch version 1.1.0+ and torchvision 0.3.0+ are needed.



3. Codes are based on Python 3



##### Data

1. Download the [WIDERFACE](http://shuoyang1213.me/WIDERFACE/WiderFace_Results.html) dataset.



2. Download annotations (face bounding boxes & five facial landmarks) from [baidu cloud](https://pan.baidu.com/s/1Laby0EctfuJGgGMgRRgykA) or [dropbox](https://www.dropbox.com/s/7j70r3eeepe4r2g/retinaface_gt_v1.1.zip?dl=0)



3. Organise the dataset directory as follows:



```Shell

  ./data/widerface/

    train/

      images/

      label.txt

    val/

      images/

      wider_val.txt

```

ps: wider_val.txt only include val file names but not label information.



##### Data1

We also provide the organized dataset we used as in the above directory structure.



Link: from [google cloud](https://drive.google.com/open?id=11UGV3nbVv1x9IC--_tK3Uxf7hA6rlbsS) or [baidu cloud](https://pan.baidu.com/s/1jIp9t30oYivrAvrgUgIoLQ) Password: ruck



## Training

We provide restnet50 and mobilenet0.25 as backbone network to train model.

We trained Mobilenet0.25 on imagenet dataset and get 46.58%  in top 1. If you do not wish to train the model, we also provide trained model. Pretrain model  and trained model are put in [google cloud](https://drive.google.com/open?id=1oZRSG0ZegbVkVwUd8wUIQx8W7yfZ_ki1) and [baidu cloud](https://pan.baidu.com/s/12h97Fy1RYuqMMIV-RpzdPg) Password: fstq . The model could be put as follows:

```Shell

  ./weights/

      mobilenet0.25_Final.pth

      mobilenetV1X0.25_pretrain.tar

      Resnet50_Final.pth

```

1. Before training, you can check network configuration (e.g. batch_size, min_sizes and steps etc..) in ``data/config.py and train.py``.



2. Train the model using WIDER FACE:

  ```Shell

  CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --network resnet50 or

  CUDA_VISIBLE_DEVICES=0 python train.py --network mobile0.25

  ```



## Evaluation

### Evaluation widerface val

1. Generate txt file

```Shell

python test_widerface.py --trained_model weight_file --network mobile0.25 or resnet50

```

2. Evaluate txt results. Demo come from [Here](https://github.com/wondervictor/WiderFace-Evaluation)

```Shell

cd ./widerface_evaluate

python setup.py build_ext --inplace

python evaluation.py

```

3. You can also use widerface official Matlab evaluate demo in [Here](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/WiderFace_Results.html)

### Evaluation FDDB



1. Download the images [FDDB](https://drive.google.com/open?id=17t4WULUDgZgiSy5kpCax4aooyPaz3GQH) to:

```Shell

./data/FDDB/images/

```



2. Evaluate the trained model using:

```Shell

python test_fddb.py --trained_model weight_file --network mobile0.25 or resnet50

```



3. Download [eval_tool](https://bitbucket.org/marcopede/face-eval) to evaluate the performance.






## TensorRT

-[TensorRT](https://github.com/wang-xinyu/tensorrtx/tree/master/retinaface)



## References

- [FaceBoxes](https://github.com/zisianw/FaceBoxes.PyTorch)

- [Retinaface (mxnet)](https://github.com/deepinsight/insightface/tree/master/RetinaFace)

```

@inproceedings{deng2019retinaface,

title={RetinaFace: Single-stage Dense Face Localisation in the Wild},

author={Deng, Jiankang and Guo, Jia and Yuxiang, Zhou and Jinke Yu and Irene Kotsia and Zafeiriou, Stefanos},

booktitle={arxiv},

year={2019}

```