Tensor的几种形状 Scalar: import torch from torch import tensor """ Tensor 常见的形式有那些: . 0 scalar . 1 vector . 2 matrix . 3 n-dimensional tensor """ # Scalar 通常就是一个数值 x = tensor(42.) print("x:\t", x) print("x.dim():\t", x.dim()) print("2*x:\t", 2*x) print("x.item():\t", x.item()) x: tensor(42.) x.dim(): 0 2*x: tensor(84.) x.item(): 42.0 Vector:向量特征,某一维度特征 import torch from torch import tensor v = tensor([1.5, -0.5, 3.0]) print("v:\t", v) print("v.dim():\t", v.dim()) print("v.size():\t", v.size()) v: tensor([ 1.5000, -0.5000, 3.0000]) v.dim(): 1 v.size(): torch.Size([3]) 3. Matrix: import torch from torch import tensor M = tensor([[1., 2.], [3., 4.]]) print("M:\t", M) M.matmul(M) print("M.matmul(M):\t", M.matmul(M)) M * M print("M*M:\t", M*M) tensor([1., 2.]).matmul(M) print("tensor([1., 2.]).matmul(M):\t", tensor([1., 2.]).matmul(M)) M: tensor([[1., 2.], [3., 4.]]) M.matmul(M): tensor([[ 7., 10.], [15., 22.]]) M*M: tensor([[ 1., 4.], [ 9., 16.]]) tensor([1., 2.]).matmul(M): tensor([ 7., 10.])