Open abuvaneswari opened 5 years ago
I also meet this problem, it seems that right results can be output when change the image reading method as the comment sentence.
did you solve the problem? I also find the pretrained model not works well. I'm new at the crowd counting field
Hello,
Thanks a lot for the very easy-to-follow instructions and the code. I am having difficulty reproducing your results. I am using your pretrained model 'PartAmodel_best.pth.tar'. And I am using the test_data set of ShanghaiTech. Getting very high MAE - in the 1000's.
PyTorch 0.4.1 CUDA 9.0 Python 2.7
Please let me know if I am doing anything wrong. Thanks, Buvana
Snippet of code (based on your val.ipynb) and result: