【torch.randn()与torch.cat()张量的生成和拼接】

torch.randn()官方解释
torch.cat()官方解释
Concatenates the given sequence of seq tensors in the given dimension. All tensors must either have the same shape (except in the concatenating dimension) or be empty.

Example:

>>> torch.randn(4)
tensor([-2.1436,  0.9966,  2.3426, -0.6366])
>>> torch.randn(2, 3)
tensor([[ 1.5954,  2.8929, -1.0923],
        [ 1.1719, -0.4709, -0.1996]])

torch.randn(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor
torch.randn()返回一个由均值为0，方差为1的正态分布(也称为标准正态分布)中的随机数填充的张量。
size定义输出张量形状的整数序列。可以是可变数量的参数，也可以是列表或元组等集合。

Example:

>>> x = torch.randn(2, 3)
>>> x
tensor([[ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497]])
>>> torch.cat((x, x, x), 0)
tensor([[ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497],
        [ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497],
        [ 0.6580, -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497]])
>>> torch.cat((x, x, x), 1)
tensor([[ 0.6580, -1.0969, -0.4614,  0.6580, -1.0969, -0.4614,  0.6580,
         -1.0969, -0.4614],
        [-0.1034, -0.5790,  0.1497, -0.1034, -0.5790,  0.1497, -0.1034,
         -0.5790,  0.1497]])

torch.cat(tensors, dim=0, *, out=None)
其中，dim是连接的维度，tensors在dim维度可以不一致，但是其他维度必须保持一致。这样才能在dim维度成功连接。