Plan freezing, a new head and cautious unfreezing to adapt a pretrained model.
Proof of success: explain "Transfer learning", complete "Freeze or Fine-Tune" and name the limit of the analogy.
Salomé's club wants to recognize three shapes of drawn leaves with only 90 examples. Training a large CNN from scratch would be fragile. The group starts from a model learned on a large allowed dataset, replaces its last layer and first freezes the extractor. After a baseline, it unfreezes a few layers with a small learning rate. Transfer reuses representations, but it also carries the limits and biases of the source.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.