- paddle.fluid.layers.nn. expand ( x, expand_times, name=None )
Warning: API “paddle.fluid.layers.nn.expand” is deprecated since 2.0.0, and will be removed in future versions. Please use “paddle.expand” instead.
paddle.expand :alias: paddle.expand,paddle.tensor.expand,paddle.tensor.manipulation.expand :old_api: paddle.fluid.layers.expand
This operation tiles
xmultiple times according to the parameter
expand_times. The times number for each dimension of
xis set by the parameter
expand_times. The rank of
xshould be less than or equal to 6. Please note that size of
expand_timesmust be the same with X’s rank. Following is a using case:
Input(X) is a 3-D tensor with shape [2, 3, 1]: [ [, , ], [, , ] ] Attr(expand_times): [1, 2, 2] Output(Out) is a 3-D tensor with shape [2, 6, 2]: [ [[1, 1], [2, 2], [3, 3], [1, 1], [2, 2], [3, 3]], [[4, 4], [5, 5], [6, 6], [4, 4], [5, 5], [6, 6]] ]
x (Variable): A
LoDTensorwith dimension in [1, 6]. The data type is
int32. expand_times (list|tuple|Variable): The data type is
expand_timesis a list or tuple, the elements of
it should be integers or Tensors with shape . If
expand_timesis an Variable, it should be an 1-D Tensor. Expand times number for each dimension of
name (str, optional): The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name .
LoDTensor. The data type is same as
x. After expanding, size of each dimension of output is equal to the size of the corresponding dimension of
xmultiplying the corresponding value given by
TypeError: The type of
expand_timesmust be list, tuple or Variable. ValueError: The elements of
expand_timescannot be negative.
import paddle.fluid as fluid # example 1: data_1 = fluid.layers.fill_constant(shape=[2, 3, 1], dtype='int32', value=0) expanded_1 = fluid.layers.expand(data_1, expand_times=[1, 2, 2]) # the shape of expanded_1 is [2, 6, 2]. # example 2: data_2 = fluid.layers.fill_constant(shape=[12, 14], dtype="int32", value=3) expand_times = fluid.layers.fill_constant(shape=, dtype="int32", value=4) expanded_2 = fluid.layers.expand(data_2, expand_times=expand_times) # the shape of expanded_2 is [48, 56].