text.py 文件源码

def ctc_label_dense_to_sparse(labels, label_lengths, batch_size):
    # The second dimension of labels must be equal to the longest label length in the batch
    correct_shape_assert = tf.assert_equal(tf.shape(labels)[1], tf.reduce_max(label_lengths))
    with tf.control_dependencies([correct_shape_assert]):
        labels = tf.identity(labels)

    label_shape = tf.shape(labels)
    num_batches_tns = tf.stack([label_shape[0]])
    max_num_labels_tns = tf.stack([label_shape[1]])
    def range_less_than(previous_state, current_input):
        return tf.expand_dims(tf.range(label_shape[1]), 0) < current_input

    init = tf.cast(tf.fill(max_num_labels_tns, 0), tf.bool)
    init = tf.expand_dims(init, 0)
    dense_mask = tf.scan(range_less_than, label_lengths, initializer=init, parallel_iterations=1)
    dense_mask = dense_mask[:, 0, :]

    label_array = tf.reshape(tf.tile(tf.range(0, label_shape[1]), num_batches_tns),
          label_shape)
    label_ind = tf.boolean_mask(label_array, dense_mask)

    batch_array = tf.transpose(tf.reshape(tf.tile(tf.range(0, label_shape[0]), max_num_labels_tns), tf.reverse(label_shape, [0])))
    batch_ind = tf.boolean_mask(batch_array, dense_mask)

    indices = tf.transpose(tf.reshape(tf.concat([batch_ind, label_ind], 0), [2, -1]))
    shape = [batch_size, tf.reduce_max(label_lengths)]
    vals_sparse = gather_nd(labels, indices, shape)

    return tf.SparseTensor(tf.to_int64(indices), vals_sparse, tf.to_int64(label_shape))

# Validate and normalize transcriptions. Returns a cleaned version of the label
# or None if it's invalid.