RuntimeError: Given groups=1, weight of size 4 125 1 1, expected input[1, 128, 56, 56] to have 125 channels, but got 128 channels instead

[albert-ba]

Hi I'm running with the following command line:
CUDA_VISIBLE_DEVICES=0,1 python train_autodeeplab.py --dataset coco --filter_multiplier 4 --resize 358 --crop_size 224 --batch-size 2
This gives me:
RuntimeError: Given groups=1, weight of size 4 125 1 1, expected input[1, 128, 56, 56] to have 125 channels, but got 128 channels instead

I understand what the error about, but I can't really fix it, why I'm getting this error?

Thanks.

[NoamRosenberg]

@BBarak Hi sorry, this one is our bad. Someone merged broken code this morning. It should be working now, can you give it a try and let me know?

[albert-ba]

I'm getting this error now:
"ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 20, 1, 1])" I saw in the closed issues that this was solved..

[NoamRosenberg]

@albert-ba are you using the most recent version of the code? It should be much smaller now. Would allow you to use batch 2 on a single machine.

[albert-ba]

Thanks