Few Shot Learning Python Packages

setfit

Efficient few-shot learning with Sentence Transformers

medmnist

[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification

paddlefsl

FSL-Mate: A collection of resources for few-shot learning (FSL).

finetuner

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.

adapt

Awesome Domain Adaptation Python Toolbox

ibbi

The Intelligent Bark Beetle Identifier (IBBI) is a Python package that provides a simple and unified interface for detecting and classifying bark and ambrosia beetles from images. https://joss.theoj.org/papers/10.21105/joss.08796

sieves

Plug-and-play document AI with zero-shot models.

personagent

A group-chat character that knows when to stay quiet and learns from being corrected, with an evidence ledger, rollback and a measured eval. QQ, Telegram, Discord and more through AstrBot, Koishi or Matrix.

fewsoldataloader

This repo hosts the PyTorch dataloader for FewSOL dataset | ICRA 2023

torchmeta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

easyfsl

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

adaptshot

Few-shot image classification on an ordinary CPU, offline, with conformal prediction sets that say how much to trust each answer and a human-in-the-loop correction path. Torch-free ONNX inference, 120 MB, Python 3.10+.

mdpo-llm

Incremental Markdown translation with LLMs — track blocks in PO files, only retranslate what changed

meta-learning-toolkit

meta-learning toolkit for Artificial Intellgence (AI) development

adaptation

Awesome Domain Adaptation Python Toolbox

cross-transformers-pytorch

Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

insurance-thin-data

Transfer learning and foundation models for thin-segment pricing - GLMTransfer, TabPFN wrapper, MMD shift test

tinyintent

A small, portable intent classifier — frozen bge-large embeddings, a linear head, and a trained cross-encoder reranker. Few-shot, CPU, no LLM in the loop.

fusionsent

Repository of the ICNLSP 2024 paper "Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes"

tlidb

Transfer Learning in Dialogue Benchmarking Toolkit

proto-clip-toolkit

Code release for Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning | IROS 2024

audiosetfit

Efficient few-shot audio classification with contrastive fine-tuning.

mmfewshot

OpenMMLab FewShot Learning Toolbox and Benchmark

metavisionary

It empowers users to train machine learning models efficiently even when confronted with datasets containing a limited number of samples and classes that bear resemblance to each other.