PyTorch: meshgrid的用法(与tensorflow的差异)

meshgrid

 Example::

        >>> x = torch.tensor([1, 2, 3])
        >>> y = torch.tensor([4, 5, 6])
        >>> grid_x, grid_y = torch.meshgrid(x, y)
        >>> grid_x
        tensor([[1, 1, 1],
                [2, 2, 2],
                [3, 3, 3]])
        >>> grid_y
        tensor([[4, 5, 6],
                [4, 5, 6],
                [4, 5, 6]])

tensorflow:

x = np.array([1, 2, 3])
y = np.array([4, 5, 6])
grid_x, grid_y = tf.meshgrid(x, y)
sess = tf.Session()
print(sess.run(grid_x))
print(sess.run(grid_y))

results:
[[1 2 3]
 [1 2 3]
 [1 2 3]]
[[4 4 4]
 [5 5 5]
 [6 6 6]]

做代码重构的时候发现tensorflow和pytorch的meshgrid的实现是不一致的,要保持一致需要后续进行transpose和reshape操作,以此简单记录.