Add BeitForSemanticSegmentation #14096
Merged
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
sgugger
approved these changes
Oct 21, 2021
| bias=bias, | ||
| dilation=dilation, | ||
| ) | ||
| self.bn = nn.BatchNorm2d(out_channels) |
There was a problem hiding this comment.
Note that this is the first module I see adding a BatchNorm layer, so if used in the Trainer, we should probably add stuff to handle the weight decay.
|
@NielsRogge |
|
Hi @kamalkraj, Yes I do plan to add that. However, this will become easier once the Image feature will be available in the Datasets library. |
|
Okay @NielsRogge I can update the flax version of beit, after this PR merge |
LysandreJik
approved these changes
Oct 26, 2021
NielsRogge
force-pushed
the
add_beit_semantic
branch
from
fc42e93 to
e61b580
Compare
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR is a follow-up of #12994, and adds the semantic segmentation head of BEiT. It's the state-of-the-art model currently for semantic segmentation (i.e. the task of labeling each pixel of an image), on datasets like ADE20k and CityScapes (see this chart on paperswithcode).
Now it's easily available with a HuggingFace API! :)
Models are on the hub: https://huggingface.co/models?search=ade-640
Here's a notebook for quick inference: https://colab.research.google.com/drive/1AS3z0plOhWWibBvDgsQkRbfJB73vSsR3?usp=sharing