/MaskRCNN-Knowledge-Distillation

MaskRCNN with Knowledge Distillation

Primary LanguagePython

MaskRCNN with Knowledge Distillation

Mask RCNN with pytorch backend for pedestrian detection on Caltech dataset.

Features

  • ROI Align layer
  • Better default configurations for ResNet18 training
  • Support CityPersons

Requirements

  1. pytorch
pip install pytorch==0.4.1
pip install torchvision
  1. tensorboardX for visualization
pip install tensorboardX==1.2
pip install tensorflow

How to run the code

  1. Compiling libs
cd ./libs
make

  1. Download Caltech dateset

    Check the Caltech dataset's homepage.

  2. Add soft link to the /data folder

cd /data
ln -s /home/data/Caltech caltech
  1. Train the teacher model at first
sh exper/caltech/maskrcnn/train_test_resnet50_softmax.sh
  1. Then, train the student model
sh /exper/caltech/maskrcnn/train_test_resnet18_softmax.sh
  1. You may need to modify the .yaml file for your own training settings.

Reference

@inproceedings{chen2019learning,
    title   =   {Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation},
    author  =   {Chen, Rui and Ai, Haizhou and Shang, Chong and Chen, Long and Zhuang, Zijie},
    booktitle = {IEEE International Conference on Image Processing (ICIP)},
    year    =   {2019}
}