pytorch-vdsr issues

Multiple .h5 training files

2

Hi, dear Jiu, thank you for sharing the code. Can I use multiple .h5 files to train the network? Since a single .h5 is too large to save. For caffe,...

DanChen001

Hi, Thank you for sharing the code. I meet the following error whlie training the network. Do you know the reason? Thanks. ##################### Namespace(batchSize=128, clip=0.4, cuda=True, gpus='0', lr=0.1, momentum=0.9, nEpochs=50,...

DanChen001

Error when using --cuda in demo.py

Hi, I'm trying to run inference using the demo.py code. I did minimal changes: enable to get any king of input image and save the output image instead of displaying...

advaza

why does the implementation not use data normalization / zero-center?

4

pzz2011

run test.py has error on gpu?

1

I run test.py, and got the following error > RuntimeError: cuda runtime error (46) : all CUDA-capable devices are busy or unavailable at /pytorch/torch/lib/THC/THCStream.cpp:40 could u tell me how to...

RyanCV