Qishang Cheng

@sanghoon

@apli @szagoruyko I ran the command in README.md， and I got 67% top-1 test_acc with AT from resnet34? Did you solve the problem?

> This seems to happen when a particular data batch has size 1. Then BN breaks down. > > Which dataset are you training on? And what is your batch...

The error occurred at the last iter of the first epoch.

 I just ran the code, the len(dataset) == 10582

Interesting! When I changed the CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 to CUDA_VISIBLE_DEVICES=4,5,6,7. the code ran successfully....

 interesting. after running the main.py with 4 GPUs the mean IOU is only 75.75% not 77.14%...

Have you solved this problem? If you have solved this problem, can you share the solution with me?

I have the same problem. Have you solved it?

Thank you for your reply: I have run the following test code of torch-scatter: input: >>> from torch_scatter import scatter_max >>> import torch >>> src = torch.tensor([[2,0,1,4,3],[0,2,1,3,4]]) >>> index =...