README.md

RetinaDetection Object Detector

Introduction

RetinaDetection是基于RetinaFace修改的检测方法，原论文is a practical single-stage SOTA face detector which is initially described in arXiv technical report

Data

0. Organise the dataset directory as follows:

  data/retinaface/
    train/
      images/
      label.txt
    val/
      images/
      label.txt
    test/
      images/
      label.txt

Install

1. Install MXNet with GPU support.
2. Install Deformable Convolution V2 operator from Deformable-ConvNets if you use the DCN based backbone.
3. Type make to build cxx tools.

Training

Please check train.py for training.

1. Copy rcnn/sample_config.py to rcnn/config.py

为了获得更好的训练效果，可针对性的修改一些参数，如下：

config.TRAIN.MIN_BOX_SIZE = 5 #最小bbox
config.FACE_LANDMARK = False #使用landmark
config.USE_BLUR = False
config.BBOX_MASK_THRESH = 0
config.COLOR_MODE = 2 #增强
config.COLOR_JITTERING = 0.125

2. Download pretrained models and put them into model/.

   ImageNet ResNet50 (baidu cloud and dropbox).

   ImageNet ResNet152 (baidu cloud and dropbox).

3. Start training with sh train_model.sh.
   Before training, you can check the resnet network configuration (e.g. pretrained model path, anchor setting and learning rate policy etc..) in rcnn/config.py.

Testing

Please check test.py for testing.

Result

ToDo

释放训练好的模型

References

@inproceedings{yangsai1991@163.com,
year={2019}
}