【TF2】tf.keras.layers.Reshape文档解读

# Layer that reshapes inputs into the given shape
tf.keras.layers.Reshape(target_shape, **kwargs)

Input shape

Arbitrary, although all dimensions in the input shape must be known/fixed. Use the keyword argument input_shape (tuple of integers, does not include the samples/batch size axis) when using this layer as the first layer in a model.

Output shape

(batch_size,) + target_shape

Example

>>> # as first layer in a Sequential model
>>> model = tf.keras.Sequential()
>>> model.add(tf.keras.layers.Reshape((3, 4), input_shape=(12,)))
>>> # model.output_shape == (None, 3, 4), `None` is the batch size.
>>> model.output_shape
(None, 3, 4)

>>> # as intermediate layer in a Sequential model
>>> model.add(tf.keras.layers.Reshape((6, 2)))
>>> model.output_shape
(None, 6, 2)

>>> # also supports shape inference using `-1` as dimension
>>> model.add(tf.keras.layers.Reshape((-1, 2, 2)))
>>> model.output_shape
(None, 3, 2, 2)

建议：

这个层建议用在tf.keras.Sequential()中，如果将Reshape层单独搞成类属性，然后在call函数中单独使用，则会报错。