Pytorch向量操作(一): torch.meshgrid

torch.meshgrid(*tensors)

• tensors: 两个一维向量，如果是0维，当作1维处理

创建网格坐标
Creates grids of coordinates specified by the 1D inputs in attr:tensors.
This is helpful when you want to visualize data over some range of inputs.

返回：两个矩阵

• 第一个矩阵行相同，列是第一个向量的各个元素
• 第二个矩阵列相同，行是第二个向量的各个元素

一个直观的例子

从输出中可以看到，grid_x从左到右从上到下分别为[0,0,0,0,1,1,1,1,2,2,2,2]，grid_y从左到右从上到下分别为[0,1,2,3,0,1,2,3,0,1,2,3]，因此我们将每个元素分别组合，就能得到x到y的网格坐标了

x = torch.tensor([0, 1, 2])
y = torch.tensor([0, 1, 2, 3])
grid_x, grid_y = torch.meshgrid(x, y)
print("grid_x: ", grid_x)
print("grid_y: ", grid_y)
print(torch.cartesian_prod(x, y))
print(torch.equal(torch.cat(tuple(torch.dstack([grid_x, grid_y]))), torch.cartesian_prod(x, y)))
'''
grid_x:  
tensor([[0, 0, 0, 0],
        [1, 1, 1, 1],
        [2, 2, 2, 2]])
grid_y:  
tensor([[0, 1, 2, 3],
        [0, 1, 2, 3],
        [0, 1, 2, 3]])
tensor([[0, 0],
        [0, 1],
        [0, 2],
        [0, 3],
        [1, 0],
        [1, 1],
        [1, 2],
        [1, 3],
        [2, 0],
        [2, 1],
        [2, 2],
        [2, 3]])
True
'''