tensorflow / tensorflow/models
Question about the 201 COCO panoramic segmentation dataset categories defined in Maskconverter？
Open
Nobody has claimed this yet.
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
Isn't the standard COCO panoramic segmentation dataset only using 133 classes? Why is 201 classes defined? Did it use more data? Can you provide a dataset of 201 categories?
Contributor guide
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 by examining the 201 categories defined in Maskconverter and comparing them with the standard 133-class COCO panoramic segmentation dataset. Determine whether the additional categories come from more data, then document the explanation and dataset availability requested in the issue.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, data
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100