This collection provides performance-optimized frameworks, SDKs, and pre-trained models for AI practitioners to develop and deploy their solutions on any GPU-accelerated on-prem, cloud, and edge systems.
NVIDIA releases a new version every month for many of the NVIDIA built AI software, updated with optimized libraries, delivering higher training and inference performance on the same GPU-powered system.
We’ve also included a few pre-trained models for computer vision and speech for you to get started. See the Models page for the full list of models across vision, speech, healthcare, and more.
Computer Vision models
By pulling and using the containers and models, you accept the terms and conditions of the applicable End User License Agreement.