Transfer Learning and Fine-Tuning for Vision

show how pretrained models change the deep learning workflow.

Units

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

Module work

• Activity
• Knowledge check
• Summary