/PRNet

Code for "Progressive Refinement Network for Occluded Pedestrian Detection" in ECCV2020.

Primary LanguageJupyter Notebook

Progressive Refinement Network for Occluded Pedestrian Detection

Keras implementation of PRNet accepted in ECCV 2020.

Dependencies

  • python 2.7
  • numpy 1.12.0
  • Tensorflow 1.x
  • keras 2.0.6
  • OpenCV

Get Start

  1. Get the code.
git clone https://github.com/sxlpris/PRNet.git
  1. Install the requirements.
  pip install -r requirements.txt

  1. Download the dataset CityPersons to folder '$PRNet/data/cityperson/'.

  2. Download the initialized models ResNet-50 to folder '$PRNet/data/models/'.

  3. Train.

run *train_prnet.py*
  1. Test.
run *test_prnet.py*

Model

To help reproduce the results in our paper, we provide our model PRNet_city.hdf5 (password:imiq) trained on CityPersons.

Ackownledgment

The code of our work is based on the pipeline of "https://github.com/liuwei16/ALFNet". Thanks for the code and training protocol.