Few-shot image classification with ProtoNet

Warning

This tutorial is a stub. The example in this folder is complete and runnable – see the README and run the command below – but the narrated walkthrough has not been written yet. Tracking issue: the tutorial is marked draft: true in metadata.yml.

Prototypical Networks under N-way K-shot settings. Learn an embedding where class prototypes are the mean of their support samples, then classify query samples by distance to those prototypes.

To run the full example now:

python main.py --cfg configs/demo.yaml --gpus 1

Setup

Placeholder so the gallery builds. Replace this file using source/_shared/templates/plot.py.template.

print("See main.py in this folder for the runnable example.")