Python tf.keras.experimental.SequenceFeatures用法及代码示例

用于序列输入的层。

继承自：Layer，Module

用法

tf.keras.experimental.SequenceFeatures(
    feature_columns, trainable=True, name=None, **kwargs
)

所有 feature_columns 必须是具有相同 sequence_length 的序列密集列。该方法的输出可以输入序列网络，例如 RNN。

此方法的输出是形状为 [batch_size, T, D] 的 3D Tensor。 T 是该批次的最大序列长度，可能因批次而异。

如果多个 feature_columns 与 Di num_elements 一起给出，则它们的输出被连接起来。因此，最终的 Tensor 具有形状 [batch_size, T, D0 + D1 + ... + Dn] 。

例子：

import tensorflow as tf

# Behavior of some cells or feature columns may depend on whether we are in
# training or inference mode, e.g. applying dropout.
training = True
rating = tf.feature_column.sequence_numeric_column('rating')
watches = tf.feature_column.sequence_categorical_column_with_identity(
    'watches', num_buckets=1000)
watches_embedding = tf.feature_column.embedding_column(watches,
                                            dimension=10)
columns = [rating, watches_embedding]

features = {
 'rating':tf.sparse.from_dense([[1.0,1.1, 0, 0, 0],
                                             [2.0,2.1,2.2, 2.3, 2.5]]),
 'watches':tf.sparse.from_dense([[2, 85, 0, 0, 0],[33,78, 2, 73, 1]])
}

sequence_input_layer = tf.keras.experimental.SequenceFeatures(columns)
sequence_input, sequence_length = sequence_input_layer(
   features, training=training)
sequence_length_mask = tf.sequence_mask(sequence_length)
hidden_size = 32
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)