Missed TensorFlow World? Check out the recap. Learn more

tf.keras.layers.InputLayer

TensorFlow 2 version View source on GitHub

Class InputLayer

Layer to be used as an entry point into a Network (a graph of layers).

Inherits From: Layer

Aliases:

It can either wrap an existing tensor (pass an input_tensor argument) or create a placeholder tensor (pass arguments input_shape, and optionally, dtype).

It is generally recommend to use the functional layer API via Input, (which creates an InputLayer) without directly using InputLayer.

This class can create placeholders for tf.Tensors, tf.SparseTensors, and tf.RaggedTensors by choosing 'sparse=True' or 'ragged=True'.

Arguments:

  • input_shape: Shape tuple (not including the batch axis), or TensorShape instance (not including the batch axis).
  • batch_size: Optional input batch size (integer or None).
  • dtype: Datatype of the input.
  • input_tensor: Optional tensor to use as layer input instead of creating a placeholder.
  • sparse: Boolean, whether the placeholder created is meant to be sparse.
  • ragged: Boolean, whether the placeholder created is meant to be ragged. In this case, values of 'None' in the 'shape' argument represent ragged dimensions. For more information about RaggedTensors, see https://www.tensorflow.org/guide/ragged_tensors.
  • name: Name of the layer (string).

__init__

View source

__init__(
    input_shape=None,
    batch_size=None,
    dtype=None,
    input_tensor=None,
    sparse=False,
    name=None,
    ragged=False,
    **kwargs
)