huggingface / huggingface/computer-vision-course
Update the chapter Vision Transformers - 0
Open
- Dominant language
- Jupyter Notebook
- Stars
- 881
- Forks
- 242
- Avg merge
- 2m
- Merged PRs (30d)
- 1
Description
## Objective
I was going through the course and I noticed some issues with the [chapter of Intro to VT](https://huggingface.co/learn/computer-vision-course/en/unit3/vision-transformers/vision-transformers-for-image-classification) . It looked less organized to me. I think the following sections should be added
### Tasks
- [ ] summary to the Vision transformer
- [ ] pros and cons of VT and CNN
Contributor guide
Assessment
This issue has not been assessed yet.