-
## Issue description
Facing the issue **Exception in device=TPU:0: torch_xla/csrc/helpers.cpp:510** while training in kaggle TPU
## Code example
 is really interesting: on the last column of Table-2, all the methods onl…
-
Have anyone tried on it?
innat updated
4 years ago
-
I'm very interested in your work and recently I've been trying to use it in the segmentation problem and here I have a couple of questions, one, how does this formula： loss = criterion(output, target_…
-
@sayakpaul @MorganR
The issue with the profiler was resolved about a day ago. Since then, I've been trying to optimize the input pipeline. Following are my observations:
1. Our current input pi…
-
Hey there,
Awesome work, the results on FFHQ 256x256 are stunning. I was able to get this code to converge on FFHQ to a similar quality as shown in the paper (after 3 or so random seeds which diverge…
-
Thanks for your sharing.
But I have a question about how to implement 'ResNet-50 + Feature Cutmix', since if we just use the replace operation like we did in the image level cutmix, the gradients w…
-
When I employ CutMix, the results get worse instead. What is important to keep in mind when I use CutMix?