torch.meshgrid 和 numpy.meshgrid的区别

torch.meshgrid 和 numpy.meshgrid的输出方向不同。

###输入
import torch
import numpy as np
x = torch.arange(3)
y = torch.arange(10,14)
print(torch.meshgrid([x,y]))
print(np.meshgrid(x.numpy(), y.numpy()))

###torch.meshgrid()输出
x=tensor([[0, 0, 0, 0],
         [1, 1, 1, 1],
         [2, 2, 2, 2]]), 
 y=tensor([[10, 11, 12, 13],
         [10, 11, 12, 13],
         [10, 11, 12, 13]])

###numpy.meshgrid()输出
[array([[0, 1, 2],
        [0, 1, 2],
        [0, 1, 2],
        [0, 1, 2]]), 
 array([[10, 10, 10],
        [11, 11, 11],
        [12, 12, 12],
        [13, 13, 13]])]