meetps / meetps/pytorch-semseg

Any one can reproduce pspnet result?

Open
#166 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.4k
Forks
786
PR merge metrics
No merged PRs in 30d

Description

I can only achieve a mIoU of ~ 52% using the trained model of PSPNet on the val set even with the full resolution on cityscapes with this psp model, which is far away from the reported result. I didn't train, just validate on the trained pspnet101_cityscapes.caffemodel published by the team of PSPNet, and it should directly get the reported result. Any one reproduce the result successfully?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Begin with the PSPNet validation path and the pspnet101_cityscapes.caffemodel on the Cityscapes validation set, using full resolution as described. Compare the resulting mIoU with the reported result and record the exact configuration; done means reproducing the discrepancy with evidence or identifying the configuration difference.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.