prototypical-networks and prototypical-network-pytorch
These are competing implementations of the same algorithm, with A being the original reference implementation from the paper's authors and B being a community reimplementation in PyTorch that may offer different framework choices or modernized code.
About prototypical-networks
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
This code helps machine learning researchers and practitioners explore "few-shot learning" by implementing Prototypical Networks. It takes in small datasets (like Omniglot) where each class has only a few examples, and outputs a trained model capable of classifying new, unseen examples from those classes. This is for researchers working on novel machine learning approaches where data is scarce for many categories.
About prototypical-network-pytorch
yinboc/prototypical-network-pytorch
A re-implementation of "Prototypical Networks for Few-shot Learning"
This project helps machine learning researchers and practitioners explore 'few-shot learning' scenarios. It takes image datasets with limited examples per category and trains a model to classify new, unseen images with high accuracy, even when only one or a few examples of that category were available during training. This is useful for those developing or evaluating classification systems under data scarcity.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work