wenbin

Does the cuda version support standard convolutions?

2

Thanks for your amazing work. I want to apply your method to a standard convolution instead of a depthwise one. Does your cuda code support standard convolutions?

Hi, I tried to reproduce your experients on OxUvA dataset. I found the default batch size is 6 which is too large for a single 2080ti. Therefore, I used 2...

Training Details

5

Hi, thank for your amazing work. I want to reproduce your work using the config `train_IRN_x2.yml`, but the training is slow and will cost 4 days using the default config....