Fix: RandomJPEG bug with different devices
#2883
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
johnnv1
requested changes
Apr 14, 2024
There was a problem hiding this comment.
even though it fixes your issue, this shouldn't be necessary...
The real issue is in the random generator
which is allocating and then casting it to the wrong deviceCan you test if in this case, where you want to use the nontensor as the bounds inputs, if you use the
import torch
from kornia.augmentation import RandomJPEG
device = "cuda"
jpegq = (1.0, 50.0)
aug = RandomJPEG(jpeg_quality=jpegq, p=1.0)
aug.set_rng_device_and_dtype(device=torch.device(device), dtype=torch.float32)
example_input = torch.randn((3, 224, 224)).to(device)
res = aug(example_input)btw, should this really be necessary? cc @shijianjian @edgarriba
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Changes
Fixes #2867
Type of change
Checklist