[NOMERGE] classification reference with v1 tensor backend #6952
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
pmeier
commented
Nov 15, 2022
| @@ -17,7 +17,10 @@ def __init__( | |||
| augmix_severity=3, | |||
| random_erase_prob=0.0, | |||
| ): | |||
| trans = [transforms.RandomResizedCrop(crop_size, interpolation=interpolation)] | |||
| trans = [ | |||
| transforms.PILToTensor(), | |||
There was a problem hiding this comment.
I can't move the ConvertImageDtype transform here, because AA in v1 only supports uint8 inputs. Are we benchmarking v2 with float32 or uint8?
There was a problem hiding this comment.
We are going to test both.
datumbox
changed the base branch from
main
to
prototype-references/classification-v1
31 tasks
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Outdated suggestions cannot be applied.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.
cc @datumbox
I've run for a few iterations with
[ "--batch-size=4", "--workers=4", "--mixup-alpha=0.5", "--cutmix-alpha=0.5", "--auto-augment=augmix", "--random-erase=1.0", ]and it seemed to work.