Ibraheem Hamdi

I'm using the Carvana dataset (which is what this code is supposed to download but I kept getting unauthorized error) and I'm getting the same thing. Any idea on how...

> I used my own dataset to train U-Net,and it took a error: Either no mask or multiple masks found for the ID So how to solve it? Somehow, running...

> I used my own dataset to train U-Net,and it took a error: Either no mask or multiple masks found for the ID So how to solve it? Go to...

@milesial changing the listdir(images_dir) to glob would be an easy fix to avoid this problem. Or just mention that we need to make sure imgs and masks folders in the...

Yeah the only example I managed to get working is cifar10. Everything else is broken.

This is what I had to do to get the cifar10 example to work: - Upgrade Python from 3.6.13 to 3.7.11 - Downgrade Pytorch from 1.10.0 to 1.8.0 - Downgrade...

> The solution by @ihamdi worked for me! Thanks a lot! > > I needed to add a slight modification by doing pip install torch==1.8.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html to have a...

Solved by downgrading to torch 1.8.0 and hydra-core to 1.0.6, upgrading to python 3.7.11 from 3.6.13 (despite documentation saying 3.6 and higher is supported), and deleting caffe2_detectron_ops.dll from user/anaconda3/env/env-name/Lib/site-packages/torch/lib.

This is what I had to do to get the cifar10 example to work: - Upgrade Python from 3.6.13 to 3.7.11 - Downgrade Pytorch from 1.10.0 to 1.8.0 - Downgrade...

Same here. Trying the cifar10 example and its taking at least 5s/iteration. 390 itr/epoch means like half an hour per epoch. I can only imagine how slow it it will...