Skip to content

tersekmatija/Bayesian-CSRNet

Repository files navigation

Bayesian CSRNet

We provide a PyTorch implementation our improved CSRNet which is based on the Bayesian crowd counting, called CSRNet.

For dataset and pretrained models refer to our paper.

Instructions

1. Preprocessing data

python preprocess_dataset.py --origin_dir <directory of original data> --data_dir <directory of processed data>

2. Training

python train.py --data_dir <directory of processed data> --save_dir <directory of log and model>

3. Evaluation

python test.py --data_dir <directory of processed data> --save_dir <directory of log and model>

License

This project is modified from Bayesian Crowd Counting project and is originally licensed under MIT | Copyright (c) 2020 Zhiheng_Ma.

About

Bayesian-CSRNet

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages