#deep-learning

Speed up model training by fixing data loading.

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

Next-generation Albumentations: dual-licensed for open-source and commercial use

Deep learning software to decode EEG, ECG or MEG signals

Training Sparse Autoencoders on Language Models

Fast and accurate AI powered file content types detection

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

An Open Source Machine Learning Framework for Everyone

Active learning for systematic reviews

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and support for E2E production ML pipelines when you're ready.

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

Relax! Flux is the ML library that doesn't make you tensor

ncnn is a high-performance neural network inference framework optimized for the mobile platform

A CLI for Kubeflow.

Simplify your onnx model

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

Easiest and laziest way for building multi-agent LLMs applications.

Brevitas: neural network quantization in PyTorch

The fastai deep learning library

optimizer & lr scheduler & loss function collections in PyTorch

High-performance automatic differentiation of LLVM and MLIR.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Cloud native, scalable storage engine for various types of energy data.

Faster structured generation