-
in your code AdaptiveInstanceNorm2D normalizes a tensor across a batch and uses running_mean and running_var, so it should be called AdaptiveBatchNorm2D ?
-
hello,
when i ran "bash ./scripts/figures.sh 0 car df"
it occured errors:
+ GPU_IDS=0
+ CLASS=car
+ DATASET=df
+++ dirname ./scripts/figures.sh
++ cd ./scripts
++ pwd -P
+ SCRIPTPATH=/home…
-
Hi, thank you for uploading the code! I am trying to reimplement the original design and I came across your code, it was big help for me.
By referring to your code, I rebuilded the code from Adain…
-
Why we are not shuffle real and fake images in batch?
For example here:
https://github.com/eriklindernoren/Keras-GAN/blob/master/cgan/cgan.py#L140
-
Please refer to this issue:
https://github.com/naoto0804/pytorch-AdaIN/issues/20
-
Hi,
In AdaIN.py file, line 93 and line 99, you comment out the subtract mean value code. Can you explain why you don't need to subtract the mean value for the input image ?
-
Your paper said that "your TwinGAN architecture uses two encoders, E1 and E2". But in your blog, I saw that "As mentioned in the Facebook paper, letting the human and anime portraits share the same ne…
-
Let's make photobooth a more sustainable project. Make a confluence document for architecture and other data flow, config, deployment, notes on future development, etc.
-
The outputs after stylizing are having blue tints though my style image doesnt have much blue colour in it.I tried with different images but still the blue tint is significant in stylized image
![hus…
-
Hello! When will You open the source code?