NVIDIA NIM for VISTA-3D (Latest)

VISTA-3D NIM Documentation

• Overview
  
  • Description
  • Terms of use
  • References
• Release Notes
  
  • Release 1.0.0
• Getting Started
  
  • Core Workflows of VISTA-3D
  • Setup and Prerequisites
    
    • Hardware Requirements
    • Software Requirements
    • NGC (NVIDIA GPU Cloud) Account Setup
    • NGC CLI Tool Setup
  • Usage Instructions
    
    • Running NIM
    • Health and Liveness Checks
    • Running Inference
      
      • Method 1: Segment All Labels
      • Method 2: Segment Specific Organs
      • Method 3: Single Organ with User Points
    • Stopping the Container
    • Visualization with 3D Slicer
      
      • Installation
      • Visualization and Rendering
• Advanced Usage
  
  • Multi-GPU Load Balancing
  • Infer with Local Image Files or DICOM Folder
  • Writing Data to Local Mounted Directory
  • Override Bundle
  • Infer without TensorRT
  • Change Port
  • Image URL Restrictions
    
    • Environment Variables
  • FAQ (Frequently Asked Questions)
• Model fine-tuning
  
  • Fine-tune the Model
  • Use the fine-tuned model in NIM
  • Troubleshooting
    
    • Common Issues
    • Logs and Debugging
• API Reference
  
  • Inference Request Payload
  • Inference Example
• Model Details
  
  • Model Architecture
  • Input
  • Output
  • Software Integration
  • Inference
  • Supported Anatomy
  • Ethical Considerations
  • License
• Performance
  
  • Accuracy Performance
  • Speed Performance
    
    • Case 1
    • Case 2
    • Case 3
    • Case 4
    • Case 5
    • Case 6
• Configuration
  
  • GPU Selection
  • Shared memory flag
  • Environment Variables
  • Volumes
• Support Matrix
  
  • Models
  • Supported Hardware
    
    • GPU Microarchitecture Compatibility
    • CUDA Compute Capability