google-research / google-research/vision_transformer
training on our own dataset
Open
- Dominant language
- Jupyter Notebook
- Stars
- 12.7k
- Forks
- 1.5k
- PR merge metrics
- No merged PRs in 30d
Description
what if training on our own dataset instead of thoses in tfds?
Contributor guide
Research direction
The issue does not name a file, notebook, test, or training entry point. First inspect the repository's training notebooks and input pipeline to determine whether custom datasets are supported; the scope and completion criteria need to be defined before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100