eyalol
eyalol
Cheers Hugues, I've managed to modify the DataLoader to fit with DALES dataset, however, when I'm training the network, I'm getting: RuntimeError: CUDA out of memory. Tried to allocate 4.73...
Why is the bias term in all the convolution layers is false? Thanks!
Hello, I believe that you have a mistake in the res_block implementation: https://github.com/kim-younghan/MultiResUNet/blob/1c4a77973c18ada6dab009ed603682dfdd20c54d/multiresunet/model/MultiResUNet.py#L72-L73 You forward the input into the **same** block a couple of times, however, we need to start...