标签：PyTorch

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

A Repo For Document AI

QualityScaler - image/video AI upscaler app

PyTorch native quantization for training and inference

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

AI comic and manga translator app/browser extension for automatically translating comics, manga, manhwa, BDs, fumetti, and more in multiple languages and formats (Images, PDF, EPUB, CBR, CBZ etc).

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

LLM Finetuning with peft

Implementation of papers in 100 lines of code.

A Web UI for easy subtitle using whisper model.

A PyTorch Library for Meta-learning Research

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Images to inference with no labeling (use foundation models to train supervised models).

Pytorch framework for doing deep learning on point clouds.

[IEEE TMI Best Paper Award] Official Implementation for UNet++

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.

Deep Learning Server and CLI for Torch and TensorRT

An extension of Open3D to address 3D Machine Learning tasks

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

Distributed AI Model Training and LLM Fine-Tuning on Kubernetes

An open source library and framework for deep learning on satellite and aerial imagery.

Controllable and fast Text-to-Speech for over 7000 languages!

Machine learning on FPGAs using HLS

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Robust realtime face and facial landmark tracking on CPU with Unity integration

NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

CVNets: A library for training computer vision networks

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

OneDiff: An out-of-the-box acceleration library for diffusion models.

一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

Transformers 库快速入门教程

A Modular Framework for 3D Gaussian Splatting and Beyond

Vocal Remover using Deep Neural Networks

Toolbox of models, callbacks, and datasets for AI/ML researchers.

High Performance Serving Runtime For Interactive Super Intelligence System

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

WARNING: Katib project is DEPRECATED, users should migrate to OptimizationJob and Kubeflow Trainer

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

A PyTorch library and evaluation platform for end-to-end compression research

Add bisenetv2. My implementation of BiSeNet

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

A library for differentiable robotics on manifolds.

Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.

Brevitas: neural network quantization in PyTorch

PyTorch extensions for fast R&D prototyping and Kaggle farming