tf.contrib.feature_column.sequence_numeric_column(
key,
shape=(1,),
default_value=0.0,
dtype=tf.dtypes.float32,
normalizer_fn=None
)
Defined in tensorflow/contrib/feature_column/python/feature_column/sequence_feature_column.py
.
Returns a feature column that represents sequences of numeric data.
Example:
temperature = sequence_numeric_column('temperature')
columns = [temperature]
features = tf.parse_example(..., features=make_parse_example_spec(columns))
input_layer, sequence_length = sequence_input_layer(features, columns)
rnn_cell = tf.nn.rnn_cell.BasicRNNCell(hidden_size)
outputs, state = tf.nn.dynamic_rnn(
rnn_cell, inputs=input_layer, sequence_length=sequence_length)
Args:
key
: A unique string identifying the input features.shape
: The shape of the input data per sequence id. E.g. ifshape=(2,)
, each example must contain2 * sequence_length
values.default_value
: A single value compatible withdtype
that is used for padding the sparse data into a denseTensor
.dtype
: The type of values.normalizer_fn
: If notNone
, a function that can be used to normalize the value of the tensor afterdefault_value
is applied for parsing. Normalizer function takes the inputTensor
as its argument, and returns the outputTensor
. (e.g. lambda x: (x - 3.0) / 4.2). Please note that even though the most common use case of this function is normalization, it can be used for any kind of Tensorflow transformations.
Returns:
A _SequenceNumericColumn
.
Raises:
TypeError
: if any dimension in shape is not an int.ValueError
: if any dimension in shape is not a positive integer.ValueError
: ifdtype
is not convertible totf.float32
.