Samira Shemirani

> Very nice work. Thank you for your endeavor. I am also interested in this phenomenon. > > I see your provided [DeepLabv3](https://github.com/kazuto1011/deeplab-pytorch/blob/master/libs/models/deeplabv3plus.py), it used `output_stride=16` with `ResNet-101`. On the...

> 1. For light-weight models (UNet, ICNet) we used `learning_rate = 1e-4`. For other models we used `learning_rate = 2e-5`. Details about batch size and input size can be found...

I am trying to run the code and the version that is working for me is "pip install dgl==2.0.0". It is the oldest version that can work properly now. You...

Thank you so much and I hope it'll be solve.

Thanks!

Dear @hoechenberger I have another question, How can I access to a code or tutorial for doing all of the thing that you did on 1 participant, on for example...