[Feature Request] Random Spatial Transforms
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
I just saw the refactored transform and it looks much better. I had issues with the PIL backend of the previous transform and used to completely avoid the torchvision transform and implement the transforms I want locally using mostly opencv.
I also saw that color transforms are added in #275. These are all great! Is there a plan to add spatial transforms such as translation, rotation, shear etc.. (in general warping) augmentations. They are crucial in case of limited dataset training such as in attribute prediction, person re-id, extreme classification, etc...
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the refactored transform mentioned in the issue and the color-transform work in #275 before defining the spatial-transform scope. The requested outcome is support for warping augmentations such as translation, rotation, and shear, but the issue does not identify files, tests, or a specific API.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- opencv, python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100