Tensorflow bucketing：用序列填充

Question

给定以下代码：

def elements_gen():
    sequence = [
        [[11, 22], [22, 22], [33, 22]],
        [[33, 22], [44, 22], [55, 22], [66, 22], [77, 22]],
        [[11, 22], [22, 22]],
        [[88, 22], [99, 22], [11, 22], [22, 22]],
    ]

    label = [1, 2, 1, 2]
    for x, y in zip(sequence, label):
        yield (x, y)


def element_length_fn(x, y):
    return tf.shape(x)[0]


dataset = tf.data.Dataset.from_generator(
    generator=elements_gen,
    output_shapes=([None, 2], []),
    output_types=(tf.int32, tf.int32),
)

dataset = dataset.apply(
    tf.data.experimental.bucket_by_sequence_length(
        element_length_func=element_length_fn,
        bucket_batch_sizes=[2, 2, 2],
        bucket_boundaries=[0, 5],
        padding_values=[0, 0],
    )
)

batch = dataset.make_one_shot_iterator().get_next()

with tf.Session() as sess:
    for _ in range(4):
        print("Get_next:")
        print(sess.run(batch))

我收到以下错误：

TypeError: If shallow structure is a sequence, input must also be a sequence. Input has type: <class 'list'>.

我想要实现的是用以下元素填充序列 [0, 0]。

如果问题看起来令人困惑，请告诉我，以便我可以包含更多信息或以更清晰的方式表达自己。

Answer 1

@jdehesa 推荐的方法可以满足我的需要并生成以下代码：

def elements_gen():
    sequence = [
        [[11, 22], [22, 22], [33, 22]],
        [[33, 22], [44, 22], [55, 22], [66, 22], [77, 22]],
        [[11, 22], [22, 22]],
        [[88, 22], [99, 22], [11, 22], [22, 22]],
    ]

    label = [1, 2, 1, 2]
    for x, y in zip(sequence, label):
        yield (x, y)


def element_length_fn(x, y):
    return tf.shape(x)[0]


dataset = tf.data.Dataset.from_generator(
    generator=elements_gen, output_shapes=([None, 2], []), output_types=(tf.int32, tf.int32)
)

dataset = dataset.apply(
    tf.data.experimental.bucket_by_sequence_length(
        element_length_func=element_length_fn,
        bucket_batch_sizes=[2, 2, 2],
        bucket_boundaries=[0, 5],
        padding_values=(0,0),
    )
)

batch = dataset.make_one_shot_iterator().get_next()

with tf.Session() as sess:
    for _ in range(2):
        print("Get_next:")
        print(sess.run(batch))

Tensorflow bucketing：用序列填充

Tensorflow bucketing: Pad with a sequence

python

tensorflow

tensorflow-datasets