zhanghang1989 / zhanghang1989/PyTorch-Encoding
In file encoding/datasets/pascal_voc.py line65
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
mask = self._mask_transform(mask) should be target = self._mask_transform(target)
And in this file's init function the mode == 'testval' is missing and I assume it's the same as mode 'val'
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
Open encoding/datasets/pascal_voc.py and inspect line 65 plus the dataset init mode handling. Compare the existing val path with the requested testval behavior, then verify that the mask transformation uses the intended target and that testval behaves correctly; no test file is named in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100