Skip to content

pirakd/CSRNet

Repository files navigation

CSRNet

A pytorch CSRNET implementation for crowd counting from images.

Current naming support shanghaitech dataset.

In order to run:

  1. put the shanghai dataset under /datasets folder in the root path of the repo

  2. Set absolute paths in presets.py

  3. preprocess density maps by running prepare_dataset.py

  4. run train.py script

  5. evaluate your model with eval.py

With the example preset you can train a sub-70 MAE on ShanghaiTech_A_test.

About

A pytorch CSRNET implementation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages