Get familiar with the basics of the Pytorch Tensor framework.

Mastering Image Classification

Tensors form the fundamental building block of the PyTorch ecosystem. Various components, such as network layers, loss function, gradient descent, and optimizer, rely on underlying tensor operations. 

In this module, we will get a comprehensive overview of tensors, starting with how to create one. We will learn the many different types of tensors as well as how to concatenate and manipulate them by selecting elements, changing the shape, and more. 

By the end of this module, we will have a basic understanding of how to work with PyTorch tensors and what they allow us to do.

Basic PyTorch Tensor Manipulation for Machine Learning

## Matrix multiplication with vectors

Let us first see how we can multiply a matrix with a vector. `PyTorch` provides the `mv()` function for this purpose.


We can use `mv()` in two ways. `mv()` could be called from a tensor, or just call it from `torch.mv()`. The first parameter for `torch.mv()` is a matrix.

```python
result = torch.mv(mat, vec)
result = mat.mv(vec)
```

The code above shows two methods to multiply a matrix with a vector. You could try it below.

>**Note**: The order of the matrix and vector is critical, otherwise, you may trigger the runtime error. The first argument of `mv` should be the matrix, the second should be the vector. For example, if the matrix is an (`n×m`) tensor, then the vector should be is a 1-D tensor of size `m`.

# Matrix multiplication with vectors

Let us first see how we can multiply a matrix with a vector. `PyTorch` provides the `mv()` function for this purpose.


We can use `mv()` in two ways. `mv()` could be called from a tensor, or just call it from `torch.mv()`. The first parameter for `torch.mv()` is a matrix.

```python
result = torch.mv(mat, vec)
result = mat.mv(vec)
```

The code above shows two methods to multiply a matrix with a vector. You could try it below.

>**Note**: The order of the matrix and vector is critical, otherwise, you may trigger the runtime error. The first argument of `mv` should be the matrix, the second should be the vector. For example, if the matrix is an (`n×m`) tensor, then the vector should be is a 1-D tensor of size `m`.

In this lesson, we will look at some basic multiplication operations between matrices and vectors.

__default

Matrix Vector Multiplication

Matrix multiplication with vectors