CatalogResources
Resources
The NGC catalog offers step-by-step instructions and scripts through Jupyter Notebooks for various use cases, including machine learning, computer vision, and conversational AI. These resources help you examine, understand, customize, test, and build AI faster, while taking advantage of best practices.
Sort: Last Modified
A SSD Detection model for Endoscopy Surgical Tools
Holoscan Sample App data for Endoscopy out of body detection
Model for HoloHub Sample App for MONAI Endoscopic Tool Segmentation
Endoscopy Sample App Data
Resource
Holoscan Sample App Data for AI-based Endoscopy Tool Tracking
Ultrasound Sample App Data
Resource
Holoscan Sample App Data for AI Ultrasound Segmentation for Scoliosis
Multi-AI Sample App Data
Resource
Holoscan Sample App Data for Multi-AI Ultrasound Pipeline
Colonoscopy Sample App Data
Resource
Holoscan Sample App Data for AI Colonoscopy Segmentation of Polyps
NGC CLI
Resource
NGC CLI
GXF (x86_64)
Resource
Headers and x86_64 libraries for GXF, for use with the Holoscan SDK
Riva Skills Embedded Quick Start
Resource
Scripts and utilities for getting started with Riva Speech Skills on Embedded platforms
Riva Skills Quick Start
Resource
Scripts and utilities for getting started with Riva Speech Skills
GXF (arm64)
Resource
Headers and arm64 libraries for GXF, for use with the Holoscan SDK
NVIDIA Time Series Prediction Platform
ResourceQuick Deploy
NVIDIA Time Series Prediction Platform is a tool designed to compare easily and experiment with arbitrary combinations of forecasting models, time-series datasets, and other configurations.
TAO Toolkit Getting Started
Resource
Quick start guide for TAO Toolkit.
TAO Converter
Resource
Binary to decrypt a .etlt from TAO Toolkit and generate a TensorRT engine
DOCA Container Resources
Resource
Set of container configuration files for the various DOCA containers.
Holoscan Debian Packages
Resource
The debian packages for the Holoscan SDK
TAO Classification-tf2 Notebook
ResourceQuick Deploy
This notebook shows an example use case for classification using the Train Adapt Optimize (TAO) Toolkit.We will be using the pascal VOC dataset for the tutorial.
BERT for PaddlePaddle
Resource
BERT is a method of pre-training language representations which obtains state-of-the-art results on a wide array of NLP tasks.
TFT PyTorch codebase
Resource
PyTorch codebase for training and using TFT model
PyTorch codebase for training and using Tacotron2 and Waveglow models
SIM TensorFlow2 codebase
Resource
TensorFlow2 codebase for training and using SIM model
ConvNets PyTorch codebase
Resource
PyTorch codebase for training and using ConvNet models
BERT TensorFlow1 codebase
Resource
TensorFlow1 codebase for training and using BERT model
BERT PaddlePaddle codebase
Resource
PaddlePaddle codebase for training and using BERT model