pytorch / pytorch/vision

Pad if needed when using TenCrop and FiveCrop

Open
#1,573 1 comment 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

When using TenCrop and FiveCrop, if the source image is smaller than the aimed crop size, there will be an error like ValueError: Requested crop size (256, 256) is bigger than input size (320, 240).

Can you pad the image if needed, just as what torchvision.transforms.RandomCrop do?

Contributor guide

Open the contributing guide

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 locating the TenCrop and FiveCrop implementations and compare their behavior with the mentioned torchvision.transforms.RandomCrop behavior. Verify the failure using a source image smaller than the requested crop size, then confirm that both transforms pad as needed and produce the expected crops.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.