Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge

tfr.keras.model.Preprocessor

Interface for feature preprocessing.

The Preprocessor class is an abstract class to implement preprocess in ModelBuilder in tfr.keras.

To be implemented by subclasses:

  • __call__(): Contains the logic to preprocess context and example inputs.

Example subclass implementation:

class SimplePreprocessor(Preprocessor):

  def __call__(self, context_inputs, example_inputs, mask):
    context_features = {
        name: tf.math.log1p(
            tf.abs(tensor)) for name, tensor in context_inputs.items()
    }
    example_features = {
        name: tf.math.log1p(
            tf.abs(tensor)) for name, tensor in example_inputs.items()
    }
    return context_features, example_features

Methods

__call__

View source

Invokes the Preprocessor instance.

Args
context_inputs maps context feature keys to tf.keras.Input.
example_inputs maps example feature keys to tf.keras.Input.
mask [batch_size, list_size]-tensor of mask for valid examples.

Returns
A tuple of two dicts which map the context and example feature keys to the corresponding tf.Tensors.