PyTorch torch.vstack Function


Pytorch torch 参考手册Pytorch torch Reference Manual

torch.vstackis a function in PyTorch used to stack tensors vertically (along rows).

Function Definition

torch.vstack(tensors, *, out=None)

Usage Example

Example

import torch

# Stack 1D tensors vertically
x1 = torch.tensor([1, 2, 3])
x2 = torch.tensor([4, 5, 6])
result = torch.vstack([x1, x2])
print("1D tensors stacked vertically:")
print(f"  x1: {x1}")
print(f"  x2: {x2}")
print(f"  vstack:n{result}")

# Stack 2D tensors vertically
y1 = torch.tensor([[1, 2], [3, 4]])
y2 = torch.tensor([[5, 6], [7, 8]])
result = torch.vstack([y1, y2])
print("\n2D tensors stacked vertically:")
print(f"  y1:n{y1}")
print(f"  y2:n{y2}")
print(f"  vstack:n{result}")

# Stack multiple tensors
z1 = torch.tensor([1, 2, 3])
z2 = torch.tensor([4, 5, 6])
z3 = torch.tensor([7, 8, 9])
result = torch.vstack([z1, z2, z3])
print("\nMultiple 1D tensors stacked:")
print(f"  result:n{result}")

The output result is:

一维张量垂直堆叠:
  x1: tensor([1, 2, 3])
  x2: tensor([4, 5, 6])
  vstack:
tensor([[1, 2, 3],
        [4, 5, 6]])

二维张量垂直堆叠:
  y1:
tensor([[1, 2],
        [3, 4]])
  y2:
tensor([[5, 6],
        [7, 8]])
  vstack:
tensor([[1, 2],
        [3, 4],
        [5, 6],
        [7, 8]])

多个一维张量堆叠:
  result:
tensor([[1, 2, 3],
        [4, 5, 6],
        [7, 8, 9]])

Pytorch torch 参考手册Pytorch torch Reference Manual

Other Extensions