tuto-fsl

Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification.

What's in there?

Notebooks

• First steps into few-shot image classification

  

Code

Models:

• AbstractMetaLearner: an abstract class with methods that can be used for any meta-trainable algorithm

• Prototypical Networks

Helpers:

• EasySet: a ready-to-use Dataset object to handle datasets of images with a class-wise directory split
• TaskSampler: samples batches in the shape of few-shot classification tasks

Datasets

• CU-Birds: we provide a script to download and extract the dataset, along with a meta-train/meta-val/meta-test split along classes. The dataset is ready-to-use with EasySet.

Roadmap

• Implement unit tests
• Integrate more methods:
  • Matching Networks
  • Relation Networks
  • MAML
  • Transductive Propagation Network
• Integrate non-episodic training
• Integrate more benchmarks:
  • miniImageNet
  • tieredImageNet
  • Meta-Dataset

Contribute

This project is very open to contributions! You can help in various ways:

• raise issues
• resolve issues already opened
• tackle new features from the roadmap
• fix typos, improve code quality