Mask R-CNN mask output shape
Open
Nobody has claimed this yet.
question
- Dominant language
- Jupyter Notebook
- Stars
- 9.8k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
In the example Mask R-CNN model provided here, the mask output shape is shown as masks: ('nbox', 1, 28, 28).
Where does the 28, 28 come from? I'm trying to convert my own Mask R-CNN model from PyTorch, and for those dimensions, I get the length and width of my input image.
Model and opset version:
Mask R-CNN, opset 11
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the provided Mask R-CNN example and its exported output definition, then compare the documented mask shape with the PyTorch model using opset 11. Confirm what the 28×28 dimensions represent and clarify the example documentation if the current description is misleading.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100