zhanghang1989 / zhanghang1989/PyTorch-Encoding
How should I modify coco.py to train on COCO Stuff dataset?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Hi, it's a nice work and I'm going to use this code to train on COCO Stuff dataset. Could you tell me is there any thing to change in encodingdataset/coco.py to make it compatible to load cocostuff-10k-v1.0 dataset?
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 by reading encodingdataset/coco.py and tracing how the existing COCO dataset is located, parsed, and encoded. Compare those expectations with the cocostuff-10k-v1.0 dataset; the work is done when the loader can consume that dataset and its behavior is covered by the project's available dataset checks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100