tf.keras.InputSpec

Specifies the rank, dtype and shape of every input to a layer.

tf.keras.InputSpec(
    dtype=None,
    shape=None,
    ndim=None,
    max_ndim=None,
    min_ndim=None,
    axes=None,
    allow_last_axis_squeeze=False,
    name=None
)

Layers can expose (if appropriate) an input_spec attribute: an instance of InputSpec, or a nested structure of InputSpec instances (one per input tensor). These objects enable the layer to run input compatibility checks for input structure, input rank, input shape, and input dtype for the first argument of Layer.call.

A None entry in a shape is compatible with any dimension.

dtypeExpected dtype of the input.
shapeShape tuple, expected shape of the input (may include None for dynamic axes). Includes the batch size.
ndimInteger, expected rank of the input.
max_ndimInteger, maximum rank of the input.
min_ndimInteger, minimum rank of the input.
axesDictionary mapping integer axes to a specific dimension value.
allow_last_axis_squeezeIf True, allow inputs of rank N+1 as long as the last axis of the input is 1, as well as inputs of rank N-1 as long as the last axis of the spec is 1.
nameExpected key corresponding to this input when passing data as a dictionary.

Example:

class MyLayer(Layer):
    def __init__(self):
        super().__init__()
        # The layer will accept inputs with
        # shape (*, 28, 28) & (*, 28, 28, 1)
        # and raise an appropriate error message otherwise.
        self.input_spec = InputSpec(
            shape=(None, 28, 28, 1),
            allow_last_axis_squeeze=True)

Methods

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()