Fix SegFormer Presets #2222
Merged
Fix SegFormer Presets #2222
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
|
Thank you for the PR Neel! |
divyashreepathihalli
approved these changes
Dec 7, 2023
mattdangerw
reviewed
Dec 7, 2023
| } | ||
| if preset in aliases: | ||
| preset = aliases[preset] | ||
| backbone = MiTBackbone.from_preset( |
There was a problem hiding this comment.
Could we just chain to super here? And add the mit_b preset to backbone_presets?
To hit this branch
keras-cv/keras_cv/models/task.py
Lines 134 to 141 in f64fba0
That would have the advantage of being totally uniform with how other tasks to this, I think.
There was a problem hiding this comment.
Got it, slight modifications needed to be made to the task logic here in order to pass input_shape to the backbone's from_preset method. I've managed to make the uniform flow work, thanks!
We may need to revisit this at some point.
yuvraj-wale
pushed a commit
to yuvraj-wale/keras-cv
that referenced
this pull request
Feb 8, 2024
* Fix segformer presets * Add extra SegFormer tests * Change flow, add backbone presets to SegFormer presets * Fix small formatting issue
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Outdated suggestions cannot be applied.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.
This PR enables proper functionality for SegFormer presets and adds basic tests.
The following behavior is created here:
SegFormer.from_preset("segformer_b0") -> missing required argument num_clases
SegFormer.from_preset("segformer_b0", num_classes=2) -> ok
SegFormer.from_preset("mit_b0", num_classes=2) -> the exact same