-
Hey, professor. When I write a cyclegan myself in pytorch. Then I test it on the orange2apple data set. I find the model totally corrupted. So I wonder if I should clean the dataset or just add some d…
-
Could you tell me any reason why do you ignore the instance norm in the fist down-sampling block in the unet? I have added the norm in the block but the performance worst
https://github.com/junyan…
-
Hi,
In google Collaboratory, the following comment appears and train.py does not work.
----------------- End -------------------
Traceback (most recent call last):
File "train.py", line 15, in…
-
Hello there.
We cannot use the original AoE assets.
Have a look at this work https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix which can turn zebras into horses and vice versa using learning. …
-
Hello,
Thank you for the implementation of the Wasserstein GANs mode and GP loss!
I followed the way proposed here: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/439
It works fo…
-
Helo,
I'm a rookie starting to work with cycleGAN_pix2pix. In that sense, I appreciate suggestions on this issue.
I'm getting the following error while testing the pix2pix model that i trained for…
-
Line24 and line 30 ，why are there two def ?
24------> def init_weights(self, init_type='normal', gain=0.02)**:**
'''
initialize network's weights
init_type: normal | xavier | kaiming | o…
-
Hey professor. I remember that the 2 stride conv is more stable than up-pooling (according to DCGAN). However, in your model, the downsampling part is 2 stride conv, while up-pooling in upsampling par…
-
I am having an issue with running CycleGAN on multiple GPUs. It works well when running on a single GPU (albeit very slowly, as expected) using
python3 train.py --dataroot ./datasets/cezanne2p…
-
Hi team,
Thank you very much for your great work. This is very interesting work for Transfer learning.
I want to replicate your work on my own environment. However, I only have a CPU or a singl…