README

Content locked

The catalog is public. Reading this content requires approved access.

CS 639 Assignment 3: Vision Transformers and CLIP

Google Colab Setup

Submission

Part 1: Vision Transformer (40%)

1.1: ViT Implementation (15 points) [Code]

1.2: ViT Understanding (15 points) [Writeup]

1.3: ViT Training (10 points) [Both]

Part 2: CLIP (60%)

2.1: Text Encoder Implementation (2.5 points) [Code]

2.2: Text Encoder Understanding (2.5 points) [Writeup]

2.3: CLIP Implementation (15 points) [Code]

2.4: CLIP Understanding (15 points) [Writeup]

2.5: CLIP Training (10 points) [Both]

2.6: CLIP Classification (15 points) [Both]