This wrapper allows to apply a layer to every temporal slice of an input.

Inherits From: Wrapper, Layer, Module

Every input should be at least 3D, and the dimension of index one of the first input will be considered to be the temporal dimension.

Consider a batch of 32 video samples, where each sample is a 128x128 RGB image with channels_last data format, across 10 timesteps. The batch input shape is (32, 10, 128, 128, 3).

You can then use TimeDistributed to apply the same Conv2D layer to each of the 10 timesteps, independently:

inputs = tf.keras.Input(shape=(10, 128, 128, 3))
conv_2d_layer = tf.keras.layers.Conv2D(64, (3, 3))
outputs = tf.keras.layers.TimeDistributed(conv_2d_layer)(inputs)
TensorShape([None, 10, 126, 126, 64])

Because TimeDistributed applies the same instance of Conv2D