PyTorch torch.meshgrid Function
Pytorch torch Reference Manual
torch.meshgridIt is a function in PyTorch used to create a grid from coordinate vectors. It generates coordinate tensors from multiple one-dimensional coordinate vectors.
Function Definition
torch.meshgrid(*tensors, indexing='xy')
Parameter Description:
*tensors: Input one-dimensional tensorindexing: Indexing mode, 'xy' (Cartesian) or 'ij' (matrix)
Example Usage
Example
import torch
# Create coordinate vectors
x = torch.tensor([1, 2, 3])
y = torch.tensor([4, 5])
# Create meshgrid (Cartesian indexing)
grid_x, grid_y = torch.meshgrid(x, y, indexing='xy')
print("grid_x:")
print(grid_x)
print("grid_y:")
print(grid_y)
# Create coordinate vectors
x = torch.tensor([1, 2, 3])
y = torch.tensor([4, 5])
# Create meshgrid (Cartesian indexing)
grid_x, grid_y = torch.meshgrid(x, y, indexing='xy')
print("grid_x:")
print(grid_x)
print("grid_y:")
print(grid_y)
The output is:
grid_x:
tensor([[1, 2, 3],
[1, 2, 3]])
grid_y:
tensor([[4, 4, 4],
[5, 5, 5]])
Example
import torch
# Create coordinate vectors
x = torch.tensor([1, 2, 3])
y = torch.tensor([4, 5])
# Create meshgrid (matrix indexing)
grid_x, grid_y = torch.meshgrid(x, y, indexing='ij')
print("grid_x:")
print(grid_x)
print("grid_y:")
print(grid_y)
# Create coordinate vectors
x = torch.tensor([1, 2, 3])
y = torch.tensor([4, 5])
# Create meshgrid (matrix indexing)
grid_x, grid_y = torch.meshgrid(x, y, indexing='ij')
print("grid_x:")
print(grid_x)
print("grid_y:")
print(grid_y)
The output is:
grid_x:
tensor([[1, 1],
[2, 2],
[3, 3]])
grid_y:
tensor([[4, 5],
[4, 5],
[4, 5]])
Other Extensions