TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.contrib.feature_column.sequence_categorical_column_with_identity

View source on GitHub

Returns a feature column that represents sequences of integers.

tf.contrib.feature_column.sequence_categorical_column_with_identity(
    key,
    num_buckets,
    default_value=None
)

Pass this to embedding_column or indicator_column to convert sequence categorical data into dense representation for input to sequence NN, such as RNN.

Example:

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

features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
input_layer, sequence_length = sequence_input_layer(features, columns)

rnn_cell = tf.compat.v1.nn.rnn_cell.BasicRNNCell(hidden_size)
outputs, state = tf.compat.v1.nn.dynamic_rnn(
    rnn_cell, inputs=input_layer, sequence_length=sequence_length)

Args:

  • key: A unique string identifying the input feature.
  • num_buckets: Range of inputs. Namely, inputs are expected to be in the range [0, num_buckets).
  • default_value: If None, this column's graph operations will fail for out-of-range inputs. Otherwise, this value must be in the range [0, num_buckets), and will replace out-of-range inputs.

Returns:

A _SequenceCategoricalColumn.

Raises:

  • ValueError: if num_buckets is less than one.
  • ValueError: if default_value is not in range [0, num_buckets).