Google I/O is a wrap! Catch up on TensorFlow sessions View sessions


View source on GitHub

A sequence of categorical terms where ids are set by hashing.

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


tokens = sequence_categorical_column_with_hash_bucket(
    'tokens', hash_bucket_size=1000)
tokens_embedding = embedding_column(tokens, dimension=10)
columns = [tokens_embedding]

features =, 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)

key A unique string identifying the input feature.
hash_bucket_size An int > 1. The number of buckets.
dtype The type of features. Only string and integer types are supported.

A _SequenceCategoricalColumn.

ValueError hash_bucket_size is not greater than 1.
ValueError dtype is neither string nor integer.