Pytorch——tensor.expand_as()函數示例

tensor.expand_as()這個函數就是把一個tensor變成和函數括號內一樣形狀的tensor，用法與expand（）類似。

差別是expand括號裏爲size，expand_as括號裏爲其他tensor。

舉例：

import torch
x = torch.tensor([[1], [2], [3]])
print('xsize:',x.size())
print('x:',x)

x_expand=x.expand(3,4)
print('x_expand:',x_expand)

x_expand=x.expand(-1,4)  # -1 means not changing the size of that dimension
print('x_expand:',x_expand)

x_expand_as=x.expand_as(x_expand)
print('x_expand_as:',x_expand_as)

輸出爲：

xsize: torch.Size([3, 1])
x: tensor([[1],
        [2],
        [3]])
x_expand: tensor([[1, 1, 1, 1],
        [2, 2, 2, 2],
        [3, 3, 3, 3]])
x_expand: tensor([[1, 1, 1, 1],
        [2, 2, 2, 2],
        [3, 3, 3, 3]])
x_expand_as: tensor([[1, 1, 1, 1],
        [2, 2, 2, 2],
        [3, 3, 3, 3]])