Contents Menu Expand Light mode Dark mode Auto light/dark mode
InnerEye-DeepLearning 0.7 documentation
InnerEye-DeepLearning 0.7 documentation

Overview and user guides

  • This project is now archived
  • InnerEye-DeepLearning
  • Setup
  • Windows Subsystem for Linux (WSL2)
  • Training a Hello World segmentation model
  • AzureML Setup
  • Dataset Creation
  • Building Models
  • Sample Tasks
  • Bring Your Own PyTorch Lightning Model
  • Debugging and Monitoring
  • Model Diagnostics
  • Move a model to other workspace
  • Pre-Trained Models
    • Hippocampus Segmentation Model
    • Lung Segmentation Model

Further reading for contributors

  • Software Development Process
  • Pytest and testing on CPU and GPU machines
  • Contributing
  • Model Deployment
  • Working with FastMRI models
  • Using the InnerEye code as a git submodule of your project
  • Releases
  • Training of self-supervised models
  • Changelog

API documentation

  • Machine learning
    • ML Core
      • Common
      • Lightning Components
      • Training Models
      • Testing Models
      • Configs
      • Metrics
      • Visualization
    • Models
      • Architectures
      • Blocks
      • Layers
      • Losses
    • Dataset
    • Data augmentation
    • Self-Supervised Learning (SSL)
      • SSL Lightning Containers
      • SSL Lightning Modules
      • SSL Datamodules and Datasets
      • SSL Utils
    • Configurations
      • Classification Configs
      • Regression Configs
      • Segmentation Configs
      • Self-Supervised Learning Configs
      • Other configs
    • Utils
    • Pipelines
    • Visualizers
  • Azure
  • Scripts
    • Runner
    • Submit for Inference
    • Move model
  • Common
Back to top
Edit this page

Models

Below is a list of models and various deep learning components that are available within InnerEye-DeepLearning.

  • Architectures
    • Base Model
    • U-Nets
    • Classificiation
    • Others
  • Blocks
  • Layers
  • Losses
Next
Architectures
Previous
Visualization
Copyright © Microsoft Corporation
Made with Sphinx and @pradyunsg's Furo