Visual intelligence for your home.
Implementation of Vision Transformer, a simple way to achieve SOTA
Effortless data labeling with AI support from Segment Anything
Automatically find issues in image datasets
Open Source Differentiable Computer Vision Library
Medical imaging toolkit for deep learning
The open-source tool for building high-quality datasets
Deep learning library
Fast image augmentation library and an easy-to-use wrapper
ICLR2024 Spotlight: curation/training code, metadata, distribution
Automate browser-based workflows with LLMs and Computer Vision
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
An Open Real-time Video-Language Interaction System
A Pragmatic VLA Foundation Model
Open source framework for deep learning satellite and aerial imagery
State-of-the-art Image & Video CLIP, Multimodal Large Language Models
Reference PyTorch implementation and models for DINOv3
Hub of ready-to-use datasets for ML models
Structured data extraction and instruction calling with ML, LLM
Data integration platform for ELT pipelines from APIs, databases
Bridging Reasoning and Action Prediction
LLM inference server with continuous batching & SSD caching
The largest collection of PyTorch image encoders / backbones
Open source driver assistance system
An on-premises, OCR-free unstructured data extraction