zhanghang1989 / zhanghang1989/PyTorch-Encoding

ADE20K validation accuracy

Open
#234 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
448
PR merge metrics
No merged PRs in 30d

Description

Using this command
python test.py --backbone resnet101 --base-size 640 --crop-size 576 --model-zoo EncNet_ResNet101_ADE --eval
gives me 44.31% mIoU as opposed to 44.4% reported here or 44.65% in the paper.

Am I missing anything here? Thanks!

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

Start by running the command shown in test.py with the EncNet_ResNet101_ADE model and compare its 44.31% mIoU with the 44.4% result in the linked experiment report and 44.65% in the paper. Check whether the command or evaluation setup differs from those references; done means explaining the discrepancy or identifying the configuration needed to reproduce the reported accuracy.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 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.