lucabergamini / vaegan-pytorch Goto Github PK

when i ran with

python main.py --train_folder </.../...> --test_folder</.../...>

an error occured in around line 161

loss_nle_mean(torch.mean(nle_value).data.cpu( ).numpy( )[ ])
IndexError:too many indices for array: array is 0-dimensional,but 1 were indexed

how can i solve this? thank you!

Thank you so much for your code! I have a question about reconstruct loss, I try to according to your code, and paper to write code, but with you because of my own to build the network structure cannot get the same initialization, through the experiment discovered the decrease in the reconstruction loss is the basic of my code, and your reconstruct loss is rising, I believe you generate results better, I want to ask, reconstruct loss decreasing is the phenomenon of right?

I couldn't run main.py, because of inplace operation

File "main.py", line 202, in
loss_decoder.backward(retain)graph=True)

one of the Variables needed for gradient computation has been modified by an inplace operation:[torch.cuda.FloatTensor [1024,128]], which is output 0 of AsStridedBackward0, is at version3; expected version 2 instead

Hello, I am studying VAE-GAN recently. I found that in your project you have network.py and network_1.py, and the corresponding main files are different. I wonder what the difference is ...

Hi, can you share the dataset directory structure for us? Thank you so much!

Hi, it would have been really helpful if you could provide the way to run your code. Where to specify the data folder, checkpoints folder and what not.
Thanks!

python main_1.py --train_folder </train/folder> --test_folder </test/folder>