Deep Tutorials for PyTorch

This is a series of in-depth tutorials I'm writing for implementing cool deep learning models on your own with the amazing PyTorch library.

Basic knowledge of PyTorch and neural networks is assumed.

If you're new to PyTorch, first read Deep Learning with PyTorch: A 60 Minute Blitz and Learning PyTorch with Examples.

24 Apr 2023: I've just completed the Super-Resolution and Transformers tutorials.

09 Dec 2023: Interested in chess or transformers? Check out Chess Transformers.

In each tutorial, we will focus on a specific application or area of interest by implementing a model from a research paper.

• attention

• transfer learning

• beam search | 🟢
complete Sequence Labeling | Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling | • language models

• character RNNs

• multi-task learning

• conditional random fields

• Viterbi decoding

• highway networks | 🟢
complete Object Detection | SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection | • single-shot detection

• multiscale feature maps

• priors

• multibox

• hard negative mining

• non-maximum suppression | 🟢
complete Text Classification | Hierarchical Attention Networks for Document Classification | a PyTorch Tutorial to Text Classification | • hierarchical attention | 🟡
code complete Super-Resolution | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution | • GANs — this is also a GAN tutorial

• residual connections

• sub-pixel convolution

• perceptual loss | 🟢
complete Machine Translation | Attention Is All You Need | a PyTorch Tutorial to Transformers | • transformers

• multi-head attention

• positional embeddings

• encoder-decoder architecture

• byte pair encoding

• beam search | 🟢
complete Semantic Segmentation | SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | a PyTorch Tutorial to Semantic Segmentation | N/A | 🔴
planned