- PyTorch Tutorial
- PyTorch - Home
- PyTorch - Introduction
- PyTorch - Installation
- Mathematical Building Blocks of Neural Networks
- PyTorch - Neural Network Basics
- Universal Workflow of Machine Learning
- Machine Learning vs. Deep Learning
- Implementing First Neural Network
- Neural Networks to Functional Blocks
- PyTorch - Terminologies
- PyTorch - Loading Data
- PyTorch - Linear Regression
- PyTorch - Convolutional Neural Network
- PyTorch - Recurrent Neural Network
- PyTorch - Datasets
- PyTorch - Introduction to Convents
- Training a Convent from Scratch
- PyTorch - Feature Extraction in Convents
- PyTorch - Visualization of Convents
- Sequence Processing with Convents
- PyTorch - Word Embedding
- PyTorch - Recursive Neural Networks
- PyTorch Useful Resources
- PyTorch - Quick Guide
- PyTorch - Useful Resources
- PyTorch - Discussion

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

In this chapter, we will discuss some of the most commonly used terms in PyTorch.

A PyTorch tensor is identical to a NumPy array. A tensor is an n-dimensional array and with respect to PyTorch, it provides many functions to operate on these tensors.

PyTorch tensors usually utilize GPUs to accelerate their numeric computations. These tensors which are created in PyTorch can be used to fit a two-layer network to random data. The user can manually implement the forward and backward passes through the network.

When using autograd, the forward pass of your network will define a **computational graph** − nodes in the graph will be Tensors, and edges will be functions that produce output Tensors from input Tensors.

PyTorch Tensors can be created as variable objects where a variable represents a node in computational graph.

Static graphs are nice because user can optimize the graph up front. If programmers are re-using same graph over and over, then this potentially costly up-front optimization can be maintained as the same graph is rerun over and over.

The major difference between them is that Tensor Flow’s computational graphs are static and PyTorch uses dynamic computational graphs.

The optim package in PyTorch abstracts the idea of an optimization algorithm which is implemented in many ways and provides illustrations of commonly used optimization algorithms. This can be called within the import statement.

Multiprocessing supports the same operations, so that all tensors work on multiple processors. The queue will have their data moved into shared memory and will only send a handle to another process.

Advertisements