zhanghang1989 / zhanghang1989/PyTorch-Encoding

Which index matches which class in ADE20k?

Open
#415 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

When I output with any model, I got probabilities per class on each pixel. E.g. when I run

model = encoding.models.get_model('DeepLab_ResNeSt101_ADE', pretrained=True).eval()
img = torch.randn(1,3,256,256)
output = model.evaluate(img)
print(output.shape)

I got torch.Size([1, 150, 256, 256]), since there are 150 classes in ADE20k dataset.

However, I did not find anywhere in the code, which prediction of the output[0, :, x, y] corresponds to which of the 150 classes in ADE dataset. Where can I find list of classes?

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 searching the repository for ADE20k dataset class definitions and the model output mapping used by DeepLab_ResNeSt101_ADE. Done means identifying which class name corresponds to each output index and documenting where that mapping can be found.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.