Optionally preprocess segmentation maps for MobileViT #28420
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
|
@amyeroberts Can you please review the PR? MobileViT image preprocessor is updated to accept segmentation maps inline to other preprocessors for segmentation models like that of Segformer. |
amyeroberts
reviewed
Jan 9, 2024
| @@ -58,7 +58,7 @@ | |||
|
|
|||
|
|
|||
| MOBILEVITV2_PRETRAINED_MODEL_ARCHIVE_LIST = [ | |||
| "apple/mobilevitv2-1.0-imagenet1k-256" | |||
| "apple/mobilevitv2-1.0-imagenet1k-256" "apple/mobilevitv2-1.0-voc-deeplabv3" | |||
There was a problem hiding this comment.
These shouldn't be changed
There was a problem hiding this comment.
I have removed it in 1669db1
| @@ -306,6 +321,48 @@ def preprocess( | |||
| ] | |||
|
|
|||
| data = {"pixel_values": images} | |||
|
|
|||
| if segmentation_maps is not None: | |||
There was a problem hiding this comment.
We should add two new methods to keep in line with other models e.g. SAM here:
- preprocess_image
- preprocess_mask
There was a problem hiding this comment.
Added additional methods to preprocess images and masks seperately in 877b81a
amyeroberts
approved these changes
Jan 10, 2024
|
I have corrected the error in the tests_torch. I will wait for the #28432 to be merged to fix the remaining CI tests |
…ges and segmentation masks respectively
amyeroberts
approved these changes
Jan 11, 2024
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
staghado
pushed a commit
to staghado/transformers
that referenced
this pull request
Jan 15, 2024
) * optionally preprocess segmentation maps for mobilevit * changed pretrained model name to that of segmentation model * removed voc-deeplabv3 from model archive list * added preprocess_image and preprocess_mask methods for processing images and segmentation masks respectively * added tests for segmentation masks based on segformer feature extractor * use crop_size instead of size * reverting to initial model
MadElf1337
pushed a commit
to MadElf1337/transformers
that referenced
this pull request
Jan 15, 2024
) * optionally preprocess segmentation maps for mobilevit * changed pretrained model name to that of segmentation model * removed voc-deeplabv3 from model archive list * added preprocess_image and preprocess_mask methods for processing images and segmentation masks respectively * added tests for segmentation masks based on segformer feature extractor * use crop_size instead of size * reverting to initial model
wgifford
pushed a commit
to wgifford/transformers
that referenced
this pull request
Jan 21, 2024
) * optionally preprocess segmentation maps for mobilevit * changed pretrained model name to that of segmentation model * removed voc-deeplabv3 from model archive list * added preprocess_image and preprocess_mask methods for processing images and segmentation masks respectively * added tests for segmentation masks based on segformer feature extractor * use crop_size instead of size * reverting to initial model
AjayP13
pushed a commit
to AjayP13/transformers
that referenced
this pull request
Jan 22, 2024
) * optionally preprocess segmentation maps for mobilevit * changed pretrained model name to that of segmentation model * removed voc-deeplabv3 from model archive list * added preprocess_image and preprocess_mask methods for processing images and segmentation masks respectively * added tests for segmentation masks based on segformer feature extractor * use crop_size instead of size * reverting to initial model
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?
Fixes # (issue)
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.