alexhock

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastbook

The fastai book, published as Jupyter Notebooks

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

interpret

Fit interpretable models. Explain blackbox machine learning.

ConvNeXt

Code release for ConvNeXt model

paper-qa

LLM Chain for answering questions from documents with citations

stumpy

STUMPY is a powerful and scalable Python library for modern time series analysis

modAL

A modular active learning framework for Python

dl-4-tsc

Deep Learning for Time Series Classification

pytorch_active_learning

PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book

RepPoints

Represent Visual Objects by Point Sets

AzureML-BERT

End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service

crepes

Conformal classifiers, regressors and predictive systems

convoys

Implementation of statistical models to analyze time lagged conversions

sinkhorn-transformer

Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

azureai-samples

Official community-driven Azure AI Examples

knowledge-extraction-recipes-forms

Knowledge Extraction For Forms Accelerators & Examples

pytorch-accelerated

A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases, and capable of utilizing different hardware options with no code changes required. Docs: https://pytorch-accelerated.readthedocs.io/en/latest/

rag-experiment-accelerator

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Yolov7-training

A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the model on custom (non-COCO) tasks.

SurvivalNet

Deep learning survival models

start_follow_read

Data-Discovery-Toolkit

A data discovery and manipulation toolset for unstructured data

azureml-scaffolding

RecommendByItemcf

Hadoop mapreduce. 基于ItemCF的协同过滤 物品推荐系统 Collaborative filtering goods recommendation system based on ItemCF

pixplotml

A Visualization Tool for Image-based Machine Learning Projects - Great for object-detection and image classification projects

MTLSA

A Multi-Task Learning Formulation for Survival Analysis

rnnsm

Bot-Framework-and-OCR-Extract

Bot Framework v4 and OCR Extract