Difference between revisions of "Clara"
Jump to navigation
Jump to search
| Line 5: | Line 5: | ||
<!--CONFIGURATION: OPTIONAL (|1}} means it's ON)--> | <!--CONFIGURATION: OPTIONAL (|1}} means it's ON)--> | ||
|{{#vardefine:conf|}} <!--CONFIGURATION--> | |{{#vardefine:conf|}} <!--CONFIGURATION--> | ||
| − | |{{#vardefine:exe|}} <!--ADDITIONAL INFO--> | + | |{{#vardefine:exe|1}} <!--ADDITIONAL INFO--> |
|{{#vardefine:job|}} <!--JOB SCRIPTS--> | |{{#vardefine:job|}} <!--JOB SCRIPTS--> | ||
|{{#vardefine:policy|}} <!--POLICY--> | |{{#vardefine:policy|}} <!--POLICY--> | ||
Revision as of 16:36, 29 June 2021
Description
NVIDIA Clara Train SDK for Medical Imaging
Clara Train SDK is a domain optimized developer application
framework that includes APIs for AI-Assisted Annotation, making
any medical viewer AI capable and a MONAI and PyTorch based
training framework with pre-trained models to kick start AI
development with techniques like Transfer Learning, Federated
Learning and AutoML.
AI-Assisted Annotation APIs and an Annotation server can be easily
integrated into any Medical Viewer. The training framework
includes decentralized learning techniques like Federated Learning
and Transfer Learning. It also includes techniques like AutoML for
iterative experimentation. The SDK provides pre-trained models as
Model Applications packaged as MMARS (Medical Model ARchive) to
users providing an intuitive config based environment for data
scientists and researchers to get kick-started with AI
Development.
Environment Modules
Run module spider clara to find out what environment modules are available for this application.
System Variables
- HPC_CLARA_DIR - installation directory
Additional Information
The sample work flow for using MONAI is available at: https://github.com/zephyrie/monai-gtc