Sorour Mohajerani

@rgkannan676 I've got the same problem as you on windows (Visual Studio 2019) with torch 1.8.1, torchvision 0.9.1, CUDA 10.2, and libtorch 1.10.1. I too made sure `cmake -DWITH_CUDA=on` is...

No no, I am not saying training script over Imagenet is wrong. I think when we are training a CNN like deeplab on say cityscapes training set "from scratch", we...

Here are the values for cityscapes training on 2975 images: ``` mean: [0.29866842 0.30135223 0.30561872] std: [0.23925215 0.23859318 0.2385942 ] ``` The code for calculating is [https://github.com/SorourMo/Useful-statistics-on-public-datasets/blob/master/mean_std_cityscapes.py](url)

@Javacr Thank you so much for your hint about cmake commands. I didn't know that ```enable_language``` is different from ```find_package```. I looked into the two links you in your comment....

Thank you for your explanation. > you can manually stop the training (ctr+c), I did so when I observe there is no better val-acc / m-F1 (e.g, 20-epochs), or you...