prototypical-network-pytorch and prototypical-networks-tensorflow

These two tools are competitors, as they offer independent implementations of the same foundational research paper, "Prototypical Networks for Few-shot Learning," but using different deep learning frameworks (PyTorch and TensorFlow).

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 21/25
Stars: 328
Forks: 62
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 132
Forks: 45
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

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.

few-shot-learning image-classification deep-learning-research model-prototyping

About prototypical-networks-tensorflow

abdulfatir/prototypical-networks-tensorflow

Tensorflow implementation of NIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

This project helps machine learning researchers and practitioners explore "few-shot learning" methods. You can input image datasets, like Omniglot or Mini-ImageNet, and it will output trained models that can classify new images even when they've only seen a few examples of each class. This is ideal for those working on computer vision tasks with limited data.

few-shot learning image classification computer vision research machine learning experimentation deep learning

Scores updated daily from GitHub, PyPI, and npm data. How scores work