Trending Projects

An open-source deep learning toolkit for building Speech-to-Text models and deploying them easily.

A curated list of open-source models, datasets, and benchmarks for domain-specific language models.

A YOLOv5-based object detection system for detecting safety helmets and restricted areas on construction sites.

The DeepFashion2 dataset provides clothing images and annotations for fashion-related computer vision tasks.

This repository contains samples for the MediaPipe framework, a cross-platform and customizable ML solution for live and batch media processing.

Open source collection of deep learning and reinforcement learning courses from top universities.

Optical character recognition for Japanese manga comics, built with Python and deep learning.

A face depixelizer tool based on the PULSE self-supervised photo upsampling model, built with Jupyter Notebook.

A plugin for the Neural Amp Modeler, a tool for AI-powered audio processing and generation.

A platform for exploring and experimenting with deep reinforcement learning techniques and applications.

An awesome curated list of medical-related AI/ML resources including LLMs, datasets, and benchmarks.

An efficient and reusable library for building RNNs and LSTMs in the Torch framework.

A book on feature engineering for machine learning, written in Python and JavaScript.

Official repository for the OFA (Unifying Architectures, Tasks, and Modalities) AI model, supporting various vision-language tasks.

A Python library for exploring the capabilities of large language models like GPT-3.

AI-powered web scraping and data gathering SDK for building intelligent agents and LLM apps

A PyTorch optimizer that adapts the learning rate to reduce the variance of gradients, improving training performance.

A C++ API and server for deep learning that supports popular frameworks like PyTorch, TensorFlow, and XGBoost.

A voice assistant platform that leverages AI to create an interactive and responsive virtual assistant.

An easy-to-use natural language processing library built on the Gluon deep learning framework.

An official implementation of a time series forecasting model using large language models.

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning tasks on a variety of GPUs.

Official PyTorch implementation of U-GAT-IT, an unsupervised generative adversarial network for image-to-image translation.

A PyTorch library for face parsing using a modified BiSeNet model, useful for computer vision and image processing tasks.

A Python library that uses deep learning to automatically remove or add mosaics to images and videos.

A PyTorch-based audio source separation toolkit for researchers and developers working on AI audio applications.

An AI-powered platform for building machine learning models from natural language prompts.

This repository contains the CVPR 2021 conference papers, which may be of interest to computer vision and AI developers.

A macOS CLI and MCP server that enables AI agents to capture screenshots with visual question answering.

Simplified implementations of deep learning related works for developers interested in AI and machine learning.

A tutorial on transfer learning, a fundamental technique in machine learning and AI.

A powerful multi-modal large language model family for building advanced AI chatbots and visual recognition models.

This Python library integrates the Segment Anything Model (SAM) with text prompts for image segmentation.

Open-source library for training and running inference with ColVision models for vision-language retrieval and generation.

A TypeScript-based bot for generating images using the NovelAI AI model and Stable Diffusion WebUI.

An open-source implementation of Auto GPT, an autonomous AI agent, that doesn't require paid APIs.

High-performance MLS-MPM solver for graphics and simulation applications.

An AI-powered sales agent to automate outreach and streamline the sales process.

FoundationStereo is a CVPR 2025 Best Paper Nomination project for zero-shot stereo matching using AI.

GameAISDK is a computer vision-based game AI automation framework for game developers.

Unofficial implementation of the LaneNet model for real-time lane detection in self-driving car applications.

A toolkit for self-supervised speech pre-training and representation learning.

Benchmarks for popular CNN models, useful for developers working on computer vision and deep learning projects.

Official repository for Professor Hung-yi Lee's Machine Learning course in Spring 2022.

Automated architecture search and hyperparameter optimization for PyTorch models.

LibMTL is a PyTorch library for building multi-task learning models for deep learning applications.

An open-source Jupyter Notebook project that showcases AI-powered writing and generation capabilities.

A TensorFlow implementation of the Differentiable Neural Computer, a powerful AI tool for vibe coders.

A suite of tools for implementing, training, and testing semantic segmentation models in TensorFlow.

SUSI.AI is an open-source AI server for building personal assistants and chatbots.