Learn PyTorch with project-based tutorials. These tutorials demonstrate modern techniques with readable code and use regular data from the internet.

Tutorials

Series 1: RNNs for NLP

Applying recurrent neural networks to natural language tasks, from classification to generation.

• Classifying Names with a Character-Level RNN
• WIP Generating Shakespeare with a Character-Level RNN
• Generating Names with a Conditional Character-Level RNN
• 🔥 Translation with a Sequence to Sequence Network and Attention
• Exploring Word Vectors with GloVe
• WIP Sentiment Analysis with a Word-Level RNN and GloVe Embeddings
• WIP Sentence Similarity with a Word-Level Autoencoder
• WIP Intent Parsing with Recursive Application of Recurrent Neural Networks

Series 2: RNNs for timeseries

• WIP Predicting future events with an RNN

Recommended Reading

I assume you have at least installed PyTorch, know Python, and understand Tensors:

• http://pytorch.org/ For installation instructions
• Deep Learning with PyTorch: A 60-minute Blitz to get started with PyTorch in general
• Introduction to PyTorch for former Torchies if you are a former Lua Torch user
• jcjohnson's PyTorch examples for a more in depth overview (including custom modules and autograd functions)

You should know about Recurrent Neural Networks and how they work:

• The Unreasonable Effectiveness of Recurrent Neural Networks shows a bunch of real life examples
• Deep Learning, NLP, and Representations for an overview on word embeddings and RNNs for NLP
• Understanding LSTM Networks is about LSTMs work specifically, but also informative about RNNs in general

And for more, read the papers that introduced many of these topics:

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Sequence to Sequence Learning with Neural Networks
• Neural Machine Translation by Jointly Learning to Align and Translate
• A Neural Conversational Model

Get Started

The quickest way to run these on a fresh Linux or Mac machine is to install Anaconda:

curl -LO https://repo.continuum.io/archive/Anaconda3-4.3.0-Linux-x86_64.sh
bash Anaconda3-4.3.0-Linux-x86_64.sh

Then install PyTorch:

conda install pytorch -c soumith

Then clone this repo and start Jupyter Notebook:

git clone http://github.com/spro/practical-pytorch
cd practical-pytorch
jupyter notebook

Feedback

If you have ideas or find mistakes please leave a note.