YouTipPytorch Torch Mv
# PyTorch torch.mv Function
* * PyTorch torch Reference Manual](#)
`torch.mv` is a PyTorch function for performing matrix-vector multiplication. It calculates the product of a matrix and a vector.
### Function Definition
torch.mv(input, vec, out=None)
**Parameters**:
* `input` (Tensor): Input matrix with shape (n, m).
* `vec` (Tensor): Input vector with shape (m,) or (m, 1).
* `out` (Tensor, optional): Output tensor.
**Returns**:
* `torch.Tensor`: Returns the matrix-vector product with shape (n,).
* * *
## Usage Examples
## Example
import torch
# Create matrix and vector
mat = torch.randn(3,4)
vec = torch.randn(4)
# Matrix-vector multiplication
result = torch.mv(mat, vec)
print("Matrix shape:", mat.shape)
print("Vector shape:", vec.shape)
print("Result shape:", result.shape)
print("Result:", result)
Output:
Matrix shape: torch.Size([3, 4])Vector shape: torch.Size()Result shape: torch.Size() tensor([-0.1861, 0.2482, -0.4375])
## Example - Neural Network Layer Calculation
import torch
# Simulate fully connected layer
W = torch.randn(512,256) # Weight matrix
x = torch.randn(256) # Input vector
# Calculate y = W @ x
y = torch.mv(W, x)
print("Weight matrix shape:", W.shape)
print("Input vector shape:", x.shape)
print("Output vector shape:", y.shape)
* * PyTorch torch Reference Manual](#)