Transfer Learning and Fine-Tuning for Vision

show how pretrained models change the deep learning workflow.

Units

1. Unit 07.00: 07.00 Feature extraction vs fine-tuning
2. Unit 07.01: 07.01 Freezing and unfreezing layers
3. Unit 07.02: 07.02 Choosing a pretrained backbone responsibly
4. Unit 07.03: 07.03 Small-data risks and data leakage
5. Unit 07.04: 07.04 Fine-tuning schedule and learning rates
6. Unit 07.05: 07.05 Project step: transfer-learning experiment memo

Module work

• Activity
• Knowledge check
• Summary