jflam / pytorch-tutorials

pytorch tutorials imported from https://notebooks.azure.com

Welcome to PyTorch Tutorials

To learn how to use PyTorch, begin with our Getting Started Tutorials. The 60-minute blitz is the most common starting point, and provides a broad view into how to use PyTorch from the basics all the way into constructing deep neural networks.

Each tutorial is in the form of a Jupyter notebook. You can clone this project and run them in your Azure Notebooks compute.

Additional high-quality examples are available, including image classification, unsupervised learning, reinforcement learning, machine translation, and many other applications, in PyTorch Examples

You can find reference documentation for PyTorch's API and layers at PyTorch docs or via inline help.

Check out the PyTorch Cheat Sheet for additional useful information.

Prerequisites

We highly recommend that you run the below exercises on a Data Science Virtual Machine, which you can set up using these instructions.

Getting Started

• Deep Learning with PyTorch: A 60 Minute Blitz
• Data Loading and Processing Tutorial
• Learning PyTorch with Examples - Tensors
• Learning PyTorch with Examples - Autograd
• Learning PyTorch with Examples - NN
• Transfer Learning Tutorial
• Saving and Loading Models
• What is torch.nn really?

Image

• Finetuning Torchvision Models
• Spatial Transform Networks Tutorial
• Neural Transfer Using PyTorch
• Adversarial Example Generation

Audio

• Torchaudio Tutorial

Text

• Chatbot Tutorial
• Generating Names with a Character-Level RNN
• Classifying Named with a Character-Level RNN
• Deep Learning for NLP with PyTorch
• Translation with a Sequence to Sequence Network and Attention
• Text Classification Tutorial

Generative

• DCGAN Tutorial

Reinforcement Learning

• Reinforcement Learning (DQN) Tutorial

Extending PyTorch

• Creating Extensions Using numpy and scipy

Production Usage

• Export a Model from PyTorch and Run It Using ONNX Runtime
• Deploying a Seq2Seq Model with TorchScript