NVIDIA Metropolis
NVIDIA Metropolis features GPU-accelerated SDKs and developer tools that help developers optimally build, deploy, and scale AI-enabled video analytics and IoT applications–from the edge to the cloud.
Explore the benefits
Faster builds
Use and customize high-performance, pretrained models, or your own models, to streamline deploying AI applications across a range of industries. Jump-start application development by building off modular microservices and reference applications.
Lower cost
Powerful SDKs including NVIDIA TensorRT™, DeepStream, and TAO Toolkit reduce overall solution cost by maximizing inference throughput and optimizing hardware usage on NVIDIA platforms and infrastructure.
Flexible deployments
Manage and scale AI deployments securely with Fleet Command™ and deploy with flexibility using cloud-native Metropolis Microservices and containerized apps with options for on-premise, cloud, or hybrid deployments.
Powerful tools for
AI-enabled video analytics
The Metropolis suite of SDKs provides a variety of starting points to accelerate and optimize any aspect of AI application development and deployment.
NVIDIA Omniverse™ Replicator
Generate physically accurate 3D synthetic data at scale, or build your own synthetic data tools and frameworks. Bootstrap perception AI model training and achieve accurate Sim2Real performance without having to manually curate and label real-world data.
Learn more
.jpg)

Pretrained models
Eliminate the time-consuming process of building models from scratch. Choose from over 100+ permutations of highly accurate models and generic neural network architectures or start with our task-based models to recognize human actions and poses, detect people in crowded spaces, classify vehicles and license plates, and much more.
Learn more Try pretrained models with Jupyter Notebook
TAO Toolkit
The Train, Adapt and Optimize (TAO) Toolkit is a low-code AI model development solution that lets you use the power of transfer learning to fine-tune NVIDIA pretrained models with your own data and optimize for inference–without AI expertise or a large training dataset.
Learn more Try TAO on LaunchPad

.jpg)
Many AI model frameworks
Create your AI models and applications on these popular NVIDIA-supported AI frameworks. Integrate any existing AI model into the Metropolis workflow and easily customize existing models in TensorFlow, PyTorch, and more by easily converting to TAO.
Learn more
TensorRT
This SDK for high-performance deep learning inference includes an inference optimizer and runtime that delivers low latency and high throughput, both on edge devices and within the cloud. TensorRT is supported on all popular frameworks, including TensorFlow and PyTorch. Powering NVIDIA solutions such as JetPack™ and DeepStream, TensorRT is a gateway to accelerated inferencing.
Learn more


DeepStream SDK
NVIDIA DeepStream SDK is a complete streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing, video, audio, and image understanding. It’s ideal for vision AI developers, software partners, startups, and OEMs building IVA apps and services.
Learn more Try DeepStream on LaunchPad
Triton Inference Server
The NVIDIA Triton™ open-source, multi-framework inference serves software to deploy, run, and scale AI models in production on both GPUs and CPUs. It supports all major frameworks, including TensorFlow and Pytorch, and maximizes inference throughput on any platform.
Learn more

.jpg)
Video Storage Toolkit (VST)
Easily manage and store footage for large volumes of video cameras with hardware-accelerated video decoding, streaming, and storage. Get started quickly with the included web-based user interface and take advantage of VST flexibility through intuitive REST APIs. It’s available for NVIDIA Jetson Xavier™ and Orin™ devices.
Learn more
Metropolis Microservices
This suite of cloud-native microservices and reference applications fast-tracks development and deployment of vision AI applications. Unlock business insights for a wide range of spaces, ranging from roadways to airports to retail stores, in significantly shortened development cycles.
Learn more


CUDA-X libraries
Take advantage of low-level libraries and primitives for computer vision and more that can help with pre-processing and model performance. NVIDIA® CUDA-X™, built on top of NVIDIA CUDA®, is a collection of libraries, tools, and technologies that deliver dramatically higher performance in compute-intensive algorithms spanning complex math, deep learning, and image processing.
Fleet Command
Streamline the provisioning and deployment of systems and AI applications at the edge with NVIDIA Fleet Command. A managed platform for container orchestration, it simplifies the management of distributed computing environments with the scale and resiliency of the cloud, turning every site into a secure, intelligent location.
Learn more Experience Fleet Command on LaunchPad


Cloud containers
Combine NVIDIA SDKs to create containerized applications easily with Docker, Kubernetes, and GPU Operators to deploy cloud-native solutions on Jetson, x86, and dGPU.
Learn more
Generate – Synthetic data generation
NVIDIA Omniverse™ Replicator
Generate physically accurate 3D synthetic data at scale, or build your own synthetic data tools and frameworks. Bootstrap perception AI model training and achieve accurate Sim2Real performance without having to manually curate and label real-world data.
Learn more
.jpg)
Train – Application-specific model customization

Pretrained models
Eliminate the time-consuming process of building models from scratch. Choose from over 100+ permutations of highly accurate models and generic neural network architectures or start with our task-based models to recognize human actions and poses, detect people in crowded spaces, classify vehicles and license plates, and much more.
Learn more Try pretrained models with Jupyter Notebook
TAO Toolkit
The Train, Adapt and Optimize (TAO) Toolkit is a low-code AI model development solution that lets you use the power of transfer learning to fine-tune NVIDIA pretrained models with your own data and optimize for inference–without AI expertise or a large training dataset.
Learn more Try TAO on LaunchPad


Many AI model frameworks
Create your AI models and applications on these popular NVIDIA-supported AI frameworks. Integrate any existing AI model into the Metropolis workflow and easily customize existing models in TensorFlow, PyTorch, and more by easily converting to TAO.
Learn more
Build – Powerful AI applications
TensorRT
This SDK for high-performance deep learning inference includes an inference optimizer and runtime that delivers low latency and high throughput, both on edge devices and within the cloud. TensorRT is supported on all popular frameworks, including TensorFlow and PyTorch. Powering NVIDIA solutions such as JetPack™ and DeepStream, TensorRT is a gateway to accelerated inferencing.
Learn more


DeepStream SDK
NVIDIA DeepStream SDK is a complete streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing, video, audio, and image understanding. It’s ideal for vision AI developers, software partners, startups, and OEMs building IVA apps and services.
Learn more Try DeepStream on LaunchPad
Triton Inference Server
The NVIDIA Triton™ open-source, multi-framework inference serves software to deploy, run, and scale AI models in production on both GPUs and CPUs. It supports all major frameworks, including TensorFlow and Pytorch, and maximizes inference throughput on any platform.
Learn more

_0.jpg)
Video Storage Toolkit (VST)
Easily manage and store footage for large volumes of video cameras with hardware-accelerated video decoding, streaming, and storage. Get started quickly with the included web-based user interface and take advantage of VST flexibility through intuitive REST APIs. It’s available for NVIDIA Jetson Xavier™ and Orin™ devices.
Learn more
Metropolis Microservices
This suite of cloud-native microservices and reference applications fast-tracks development and deployment of vision AI applications. Unlock business insights for a wide range of spaces, ranging from roadways to airports to retail stores, in significantly shortened development cycles.
Learn more
.jpg)

CUDA-X libraries
Take advantage of low-level libraries and primitives for computer vision and more that can help with pre-processing and model performance. NVIDIA® CUDA-X™, built on top of NVIDIA CUDA®, is a collection of libraries, tools, and technologies that deliver dramatically higher performance in compute-intensive algorithms spanning complex math, deep learning, and image processing.
Deploy – Application management and scaling
Fleet Command
Streamline the provisioning and deployment of systems and AI applications at the edge with NVIDIA Fleet Command. A managed platform for container orchestration, it simplifies the management of distributed computing environments with the scale and resiliency of the cloud, turning every site into a secure, intelligent location.
Learn more Experience Fleet Command on LaunchPad

.jpg)
Cloud containers
Combine NVIDIA SDKs to create containerized applications easily with Docker, Kubernetes, and GPU Operators to deploy cloud-native solutions on Jetson, x86, and dGPU.
Learn more
Get started with sample applications

Action recognition
Learn how to develop and deploy a no-code action recognition application using TAO and DeepStream.

Face mask detection
Integrate TAO with DeepStream for a 10X reduction in development time when creating a real-time face-detection edge application.

Pose estimation
Learn how to create a gesture recognition application with robot interactions. Also, train and optimize a 2D pose estimation model with NVIDIA TAO Toolkit.

Number plate detection
Learn how to combine TAO with DeepStream for a license plate detection and understanding app.