zhanghang1989 / zhanghang1989/PyTorch-Encoding
inconsistent split of pcontext with the benchmark?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I have run the script/prepare_pcontext.py and get the train.pth and val.pth, while the train.pth only include 4996 imgs and val.pth include 5104 img and there are 4188 imgs for test, but the pascal context only have 10103 imgs and 4998 for training 5105 for val which also mentioned in your paper, and i use the single scale of encnet on the 5104 val imgs get miou 49.5. Is the performance reasonable and about the split could you give some suggestions? Thank you.
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 running script/prepare_pcontext.py and checking the generated train.pth and val.pth counts against the Pascal Context split described in the paper. Compare the 5104-image validation result with the reported benchmark and determine whether the split or the single-scale ENet evaluation explains the 49.5 mIoU; document the confirmed counts and performance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100