The project description can be found in above in Comparison of various CNN-based approaches for Crowd Counting pdf
This is an simple and clean implemention of CVPR 2016 paper "Single-Image Crowd Counting via Multi-Column Convolutional Neural Network."
1. Install pytorch 1.0.0 later and python 3.6 later
2. Install visdom
pip install visdom
3. Clone this repository
We'll call the directory that you cloned MCNN-pytorch as ROOT.
1. Download ShanghaiTech Dataset from kaggle.
2. Put ShanghaiTech Dataset in ROOT and use "data_preparation/k_nearest_gaussian_kernel.py" to generate ground truth density-map. (Mind that you need modify the root_path in the main function of "data_preparation/k_nearest_gaussian_kernel.py")
1. Modify the root path in "train.py" according to your dataset position.
2. In command line:
python -m visdom.server
3. Run train.py
1. Modify the root path in "test.py" according to your dataset position.
2. Run test.py for calculate MAE of test images or just show an estimated density-map.