Getting Started • Table of Contents • About • Acknowledgment • FAQ • Citing
Made by XiMing Xing • 🌌 https://ximinng.github.io/
A collection of various deep learning architectures, models, and tips for PyTorch.
This repository contains many deep learning algorithms and their applications, this is how I love deep learning.
- our code requires
python >= 3.7
,torch >= 1.0
.
numpy == 1.18.2
,scipy == 1.4.1
,scikit-learn == 0.22.2
,matplotlib == 3.2.1
.
pip install torch==1.7.1+cu101 torchvision==0.8.2+cu101 -f https://download.pytorch.org/whl/torch_stable.html
-
Multilayer Perceptrons
- MLP in nn.Module
-
Convolutional Neural Networks (CNN)
- AlexNet
- VGG
-
Recurrent Neural Networks (RNN)
-
Transformer
- Bert
- GPT-2
-
Vision Transformer
- ViT
-
Diffusion Model
- DDPM
-
AutoEncoder (AE)
- VAE
-
Generative Adversarial Networks (GAN)
- basic GAN
- CycleGAN
-
Graph Neural Networks (GNN)
- DeepWalk
- Node2Vec
- Graph Convolutional network (GCN)
- GraphSage
-
Deep Reinforcement Learning
- Deep Q Learning (DQN)
- Reinforcement Learning with Model-Agnostic Meta-Learning
-
Meta Learning
- MAML
-
Tips and Tricks
One of the greatest assets of Deep Learning is the community and their contributions. A few of my favourite resources that pair well with the models and componenets here are listed below.
-
Delip Rao., & Brain McMahan., (2019). Natural Language Processing with PyTorch. Sebastopol: O'Reilly Media,Inc.
-
Tariq Rashid., (2018). Make Your Own Neural Network. Beijing: Posts & Telecom Press.
-
Tariq Rashid., (2020). Make Your First GAN with Pytorch. Beijing: Posts & Telecom Press.
-
PyTorch wrapper:
-
Tensors operations:
-
GANs:
-
Metric Learning:
-
Image Augmentation:
- albumentations (Fast Image Augmentation library.)
-
Vision Transformer:
@misc{xing_2019_dlic,
author = {Ximing Xing},
title = {Deep Learning in Action},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/ximingxing/Deep-Learning-in-Action}}
}