Vision Transformers

What you'll be able to do

Apply the transformer architecture to images — the modern alternative to CNNs powering state-of-the-art vision.

⌁ Google multimodal models, HuggingFace ViT/CLIP/DINOv2 checkpoints, Meta DINOv2, and vision encoders inside multimodal LLMs.

Start this internship

Create an account to unlock the 5 sections, the workbench, and AskThili.

Sections

1. Vision Transformers

🔒 locked

2. Introduction to Vision Transformers

🔒 locked

3. Programming ViT Model

🔒 locked

4. Using Pretrained ViTs (with Hugging Face)

🔒 locked

5. Fine Tuning ViT

🔒 locked