This is the PyTorch version repo for CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes in CVPR 2018, which delivered a state-of-the-art, straightforward and end-to-end architecture for crowd counting tasks. orginally cloned from : https://github.com/leeyeehoo/CSRNet-pytorch
Python: 3+ PyTorch CUDA: 9.2+ flask
download the pre-trained weights from here
then run file get_count_rest.py that create falsk restfull webservice you can test by upload image using test.html