Learn how to Customize EncoderMap

Some notebooks to help you in customizing EncoderMap

• Learning Rate Scheduler
  • For Google colab only:
• Logging Custom Images
  • For Google colab only:
  • Matplotlib implementation
  • Provide this function to EncoderMap
  • Train EncoderMap with our new function.
  • Output
  • Matplotlib
  • Subclassing a keras callback
  • Adding the callback to EncoderMap
  • Output
• Writing Custom Loss Functions
  • For Google colab only:
  • Build a loss function from that:
  • Include the loss function in EncoderMap
  • Train
  • Output
• Logging Custom Scalars
  • For Google colab only:
  • Getting input data
  • Setting parameters
  • Subclassing the SequentialModel
  • Changing what happens in a training step
  • Running EncoderMap with the new model