oscarknagg/few-shot
Repository for few-shot learning machine learning projects
This project provides pre-built machine learning models that can learn to classify new types of images with very few examples. You input standard image datasets like Omniglot or miniImageNet, and the models output classifications for new, previously unseen image categories, even if you only have a handful of images per category. This is ideal for machine learning researchers and practitioners who need to explore and compare few-shot learning techniques for image classification.
1,280 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner interested in evaluating and reproducing state-of-the-art few-shot image classification models using established datasets.
Not ideal if you are looking for a plug-and-play solution for general-purpose image classification without prior machine learning expertise, or if you don't have access to a GPU.
Stars
1,280
Forks
248
Language
Python
License
MIT
Category
Last pushed
Nov 25, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/oscarknagg/few-shot"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
Sha-Lab/FEAT
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"
akshaysharma096/Siamese-Networks
Few Shot Learning by Siamese Networks, using Keras.