Computer Vision
Vision Transformers
Transformers for images. Patches, ViT, and how CLIP connects pictures and text.
- Advanced
- About 6 hours
- 1 modules
- 5 lessons
- Free
This course is not released yet. We publish courses one at a time, each one complete. The full syllabus is below.
What you will learn
- ViTImages as Patches, The ViT Architecture, ViT vs CNN and more
Course syllabus
Not released yet · full syllabus below
- 1
ViT
5 lessons- 1Images as PatchesSoon
- 2The ViT ArchitectureSoon
- 3ViT vs CNNSoon
- 4CLIP: Connecting Images and TextSoon
- 5Fine-Tuning a ViTSoon