View source

Class SequenceFeatures

A layer for sequence input.


  • Class tf.compat.v1.keras.experimental.SequenceFeatures
  • Class tf.compat.v2.keras.experimental.SequenceFeatures

All feature_columns must be sequence dense columns with the same sequence_length. The output of this method can be fed into sequence networks, such as RNN.

The output of this method is a 3D Tensor of shape [batch_size, T, D]. T is the maximum sequence length for this batch, which could differ from batch to batch.

If multiple feature_columns are given with Di num_elements each, their outputs are concatenated. So, the final Tensor has shape [batch_size, T, D0 + D1 + ... + Dn].


rating = sequence_numeric_column('rating')
watches = sequence_categorical_column_with_identity(
    'watches', num_buckets=1000)
watches_embedding = embedding_column(watches, dimension=10)
columns = [rating, watches_embedding]

sequence_input_layer = SequenceFeatures(columns)
features =,
sequence_input, sequence_length = sequence_input_layer(features)
sequence_length_mask = tf.sequence_mask(sequence_length)

rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size)
rnn_layer = tf.keras.layers.RNN(rnn_cell)
outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask)


View source


"Constructs a SequenceFeatures layer.


  • feature_columns: An iterable of dense sequence columns. Valid columns are
    • embedding_column that wraps a sequence_categorical_column_with_*
    • sequence_numeric_column.
  • trainable: Boolean, whether the layer's variables will be updated via gradient descent during training.
  • name: Name to give to the SequenceFeatures.
  • **kwargs: Keyword arguments to construct a layer.


  • ValueError: If any of the feature_columns is not a SequenceDenseColumn.

results matching ""

    No results matching ""