He Zhang
> Since this is now working on the current macOS, I'm going to close this issue. @TobyRoseman Not sure why this issue is closed........ It should be a bug for...
Sorry, baiduyun account is not easy to have without Chinese Phone number. But you can also generate the sample using 'create_train.py' (Please download the NYU-depth @ http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat)
Hi Please install pytorch 0.3.1. https://pytorch.org/previous-versions/
Some people suggest the following code. It may address the issue. netG = net.dehaze(inputChannelSize, outputChannelSize, ngf) model_dict = netG.state_dict() tmpname={} i=0 for k, v in model_dict.items(): tmpname[i]=k i=i+1 i=0 if...
Thanks !!@Aleberello
Please check the pix2pix_val2.py in the datasets folder.
If you want to run without cuda and GPU, please change the code to non-gpu version. For example, please remove xx.cuda() and make all the tensor and loss functions in...
I guess 1024 should also work. However, since the network is trained on 512X512, the receptive field will be a issue. To get good results, please crop or resize to...
pytorch 0.3.x
I guess the version for cudnn may be wrong. You have to have a try on different cudnn version.