Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

Mosaic Possible Bug-Albumentation

Open
#1,688 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.6k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

I tried to fit some albumentation augmentation but aug involving bbx fails because labels generated after the mosaic operation overshot the height/width of mosaiced image.

np.clip(mosaic_labels[:, 0], 0, 2 * input_w, out=mosaic_labels[:, 0])
               np.clip(mosaic_labels[:, 1], 0, 2 * input_h, out=mosaic_labels[:, 1])
               np.clip(mosaic_labels[:, 2], 0, 2 * input_w, out=mosaic_labels[:, 2])
               np.clip(mosaic_labels[:, 3], 0, 2 * input_h, out=mosaic_labels[:, 3])

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 locating the mosaic-label clipping code shown in the report and reproduce an Albumentations bounding-box augmentation through the mosaic path. Compare generated box coordinates with the mosaiced image dimensions; done means the augmentation handles the reported case without labels exceeding those bounds.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.