App Frameworks and SDKs
Multimodal conversational AI
NVIDIA Riva is an SDK for building and deploying AI applications that fuse vision, speech and other sensors. It offers a complete workflow to build, train and deploy GPU-accelerated AI systems that can use visual cues such as gestures and gaze along with speech in context.
NVIDIA Metropolis and DeepStream
AI-enabled video analytics
NVIDIA Metropolis is an application framework that simplifies the development, deployment and scale of AI-enabled video analytics applications from edge to cloud. It includes production ready pre-trained models and TAO Toolkit for training and optimization, DeepStream SDK for streaming analytics, other deployment SDKS, CUD-X libraries and the NVIDIA EGX platform.
Explore Full Set of Tools
Data science software
The RAPIDS suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs. Licensed under Apache 2.0, RAPIDS is incubated by NVIDIA® based on extensive hardware and data science experience. RAPIDS utilizes NVIDIA CUDA® primitives for low-level compute optimization, and exposes GPU parallelism and high-bandwidth memory speed through user-friendly Python interfaces.
The NGC container registry provides researchers, data scientists, and developers with simple access to a comprehensive catalog of GPU-accelerated software for AI, machine learning and HPC - and includes performance-engineered containers featuring AI software like TensorFlow, PyTorch, MXNet, NVIDIA TensorRT™, RAPIDS and more. These containers take full advantage of NVIDIA GPUs on-premises and in the cloud. Each is fully optimized and works across a wide variety of NVIDIA GPU platforms.
NVIDIA TAO Toolkit
The term “transfer learning” implies that you can extract learned features from an existing neural network and transfer these learned features by transferring weight from an existing neural network. TAO Toolkit enables you to build high performance IVA based applications such as retail analytics, logistics, smart cities, access control and more.
NVIDIA TensorRT™ is a platform for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.
Triton Inference Server
The NVIDIA Triton inference server simplifies the deployment of AI models at scale in production. Triton Server is open-source inference server software that lets teams deploy trained AI models from many frameworks, including TensorFlow, TensorRT, PyTorch, and ONNX.
Automatic Mixed Precision
Deep Neural Network training has traditionally relied on IEEE single-precision format, however with mixed precision, you can train with half precision while maintaining the network accuracy achieved with single precision. This technique of using both single- and half-precision representations is referred to as mixed precision technique.
NVIDIA ISAAC SDK
Robotics SDK | Learn More
Build and deploy commercial-grade, AI-powered robots. The NVIDIA Isaac SDK™ is a toolkit that includes building blocks and tools that accelerate robot developments that require the increased perception and navigation features enabled by AI.
Recommendation system framework | Get Started
Merlin empowers data scientists, machine learning engineers, and researchers to build high-performing recommenders at scale. Merlin includes tools that democratize building deep learning recommenders by addressing common ETL, training, and inference challenges. Each stage of the Merlin pipeline is optimized to support hundreds of terabytes of data, all accessible through easy-to-use APIs. With Merlin, better predictions than traditional methods and increased click-through rates are within reach.
Cybersecurity app framework | Apply for early access
NVIDIA Morpheus is an open AI application framework that provides cybersecurity developers with a highly optimized AI pipeline and pre-trained AI capabilities that, for the first time, allow them to instantaneously inspect all IP traffic across their data center fabric. Bringing a new level of security to data centers, Morpheus provides dynamic protection, real-time telemetry, adaptive policies, and cyber defenses for detecting and remediating cybersecurity threats.
Browse by Resource Type
Create Intelligent Places Using NVIDIA Vision AI Models & DeepStream SDK
This webinar will briefly introduce new features of DS5.0 and TAO Toolkit 2.0, and show an end-to-end demo using Peoplenet/DS/TAO Toolkit, for people counting/occupancy analytics, which can be used widely in retail stores or public spaces.
Driving Agility in Retail with AI
AI is helping retailers not only keep employees and customers safe, but also improve business agility to increase e-commerce sales, improve contactless checkout in stores, reduce shrink, and accelerate distribution center automation. Learn how the most innovative retailers are using AI to deliver the greatest business value.
Using Pre-Trained Models and TAO Toolkit 3.0 for Robotics
Learn how to train your own gesture recognition deep learning pipeline. We’ll start with a pre-trained detection model, repurpose it for hand detection, and use it together with the purpose-built gesture recognition model.
Getting Started with DeepStream for Video Analytics on Jetson Nano
You’ll learn how to:
- Set up your Jetson Nano and (optional) camera
- Build end-to-end DeepStream pipelines to convert raw video input into insightful annotated video output
- Configure multiple video streams simultaneously
Fundamentals of Accelerated Data Science with RAPIDS
You’ll learn how to:
- Use cuDF, Dask, and BlazingSQL to manipulate massive datasets directly on the GPU
- Utilize a wide variety of GPU-accelerated machine learning algorithms including XGBoost, cuGRAPH, and several cuML algorithms to perform data analysis at massive scale
- Perform multiple analysis tasks on several massive datasets in an effort to stave off a simulated epidemic outbreak affecting the entire UK population
Building Intelligent Recommender Systems
You’ll learn how to:
- Build a content-based recommender system using the open-source cuDF library and Apache Arrow
- Optimize performance for both training and inference using large, sparse datasets
- Deploy a recommender model as a high-performance web service
AI Workflows for Intelligent Video Analytics with Deep Stream
You’ll learn how to:
- Deploy DeepStream pipeline for parallel, multi-stream video processing and deliver applications with maximum throughput at scale
- Configure the processing pipeline and create intuitive, graph-based applications.
- Leverage multiple deep network models to process video streams and achieve more intelligent insights
Interactively Visualizing a DriveTime Radius from Any Point in the US
Retailers who understand these factors have an advantage over their competitors and can thrive. In this blog post, we’ll explore how RAPIDS’ cuDF, cuGraph, cuSpatial, and Plotly Dash with NVIDIA GPUs can be used to solve these complex geospatial analytics problems interactively.
Best Practices of Using AI to Develop an Accurate Forecasting Solution
Learn about the best practices of using AI and data science to improve forecasting in retail. This blog explains the Instacart Market Basket Analysis Kaggle competition, how to explore the data visually, train the model and run a forecasting predictio.
Beginner’s Guide to GPU- Accelerated Event Stream Processing in Python
Learn about the various aspects of RAPIDS that allow its users solve ETL (Extract, Transform, Load) problems, build ML (Machine Learning) and DL (Deep Learning) models, explore expansive graphs, process geospatial, signal, and system log data, or use SQL language via BlazingSQL to process data.
PROGRAMS FOR YOU
The NVIDIA Developer Program provides the advanced tools and training needed to successfully build applications on all NVIDIA technology platforms. This includes access to hundreds of SDKs, a network of like-minded developers through our community forums, and more.
NVIDIA Deep Learning Institute (DLI) offers hands-on training in AI, accelerated computing, and accelerated data science to solve real-world problems. Powered by GPUs in the cloud, training is available as self-paced, online courses or live, instructor-led workshops.
Accelerate Your Startup
NVIDIA Inception—an acceleration platform for AI, data science, and HPC startups—supports over 7,000 startups worldwide with go-to-market support, expertise, and technology. Startups get access to training through the DLI, preferred pricing on hardware, and invitations to exclusive networking events.
NVIDIA Retail News
Develop, Deploy, and Distribute Immersive Experiences with NVIDIA CloudXR and Amazon Web Services
Use NVIDIA CloudXR alongside AWS to build immersive XR experiences from the cloud for key advantages at every stage from development to distribution.
World’s Largest Manufacturing Players Tapping NVIDIA AI Platform for Factory of the Future
Tapping into the NVIDIA AI platform and Microsoft Azure Infrastructure, Sight Machine accurately maps data to assets at a global scale.
Theia Interactive Generates Realistic and Interactive Scenes with DLSS and RTX Global Illumination
Learn how by integrating NVIDIA technologies, Theia Interactive has reduced the time it takes for ray tracing and rendering.
Transform the Future with Robotics at NVIDIA GTC
Over 15 sessions will be presented covering autonomous machines and robotics-specific topics.
View all retail news
Sign up for the latest developer news from NVIDIA