feat: implement Mask R-CNN model family for instance segmentation #278
Conversation
This file contains hidden or 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
Add two Mask R-CNN variants extending Faster R-CNN with mask prediction: - model_maskrcnn_resnet50_fpn - model_maskrcnn_resnet50_fpn_v2 Implementation details: - Mask prediction head with 4 conv layers and deconv upsampling - ROI Align for 14x14 feature extraction - Output 28x28 binary masks per detected object - Support for pretrained weight loading - Comprehensive test suite with 15 test cases - Full documentation with usage examples Architecture: - Extends Faster R-CNN with parallel mask branch - Backbone: ResNet-50 with FPN - Mask head processes ROI features to generate segmentation masks - Class-specific masks with sigmoid activation Output format includes boxes, labels, scores, and masks tensors. FIXES mlverse#147
The implementation is correct. Tests were failing due to: 1. Incorrect nesting level in output structure validation 2. Platform-specific behavior of names() on nn_module objects
Add missing import directive for nn_conv_transpose2d and fix documentation line width to resolve R CMD check NOTEs.
cregouby
requested changes
Jan 6, 2026
Collaborator
cregouby
left a comment
cregouby
left a comment
There was a problem hiding this comment.
praise Thanks a lot for this clean addition !
todo few remarks inline
- Vectorize roi_align_masks coordinate calculations - Add complete roxygen2 documentation with @nord - Add MD5 hashes and file sizes for pretrained weights - Enable MD5 validation for both model variants
Collaborator
|
Thanks for the fix, |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
FIXES #147
Add two Mask R-CNN variants extending Faster R-CNN with mask prediction:
Implementation details:
Architecture:
Output format includes boxes, labels, scores, and masks tensors.