keywords: DeepLearning, Tools, Frameworks, Examples & Papers

Architecture

RegNet

Nonrigid image registration using multi-scale 3D convolutional neural networks
https://github.com/hsokooti/RegNet

Codebase for Image Classification Research, written in PyTorch.
https://github.com/facebookresearch/pycls

Pytorch implementation of network design paradigm described in the paper “Designing Network Design Spaces”
https://github.com/signatrix/regnet

Facebook AI RegNet Models Outperform EfficientNet Models, Run 5x Faster on GPUs
https://medium.com/syncedreview/facebook-ai-regnet-models-outperform-efficientnet-models-run-5x-faster-on-gpus-7bdc3ea577ae

Platform

PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration.
https://github.com/pytorch/pytorch

Fine-tune pretrained Convolutional Neural Networks with PyTorch
https://github.com/creafz/pytorch-cnn-finetune

Colossal

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training
https://github.com/hpcaitech/ColossalAI

Sources

Comprehensive Library

Open Source Computer Vision Library
https://github.com/opencv/opencv

A collection of various deep learning architectures, models, and tips
https://github.com/rasbt/deeplearning-models

Machine learning, in numpy
https://github.com/ddbourgin/numpy-ml

Virginia Tech Vision and Learning Lab
https://github.com/vt-vl-lab

scikit-learn: machine learning in Python
https://scikit-learn.org/
https://github.com/scikit-learn/scikit-learn

Cross-platform, customizable ML solutions for live and streaming media. Face Detection, Face Mesh, Iris, Hands, Pose, Holistic.
https://github.com/google/mediapipe

Management Tools

Fastest unstructured dataset management for TensorFlow/PyTorch. Stream data real-time & version-control it.
https://github.com/activeloopai/Hub

This repository includes optimized deep learning models and a set of demos to expedite development of high-performance deep learning inference applications. Use these free pre-trained models instead of training your own models to speed-up the development and production deployment process.
https://github.com/openvinotoolkit/open_model_zoo

This toolkit allows developers to deploy pre-trained deep learning models through a high-level C++ Inference Engine API integrated with application logic.
https://github.com/openvinotoolkit/openvino

Recommender System

An open source recommender system service written in Go.
https://github.com/zhenghaoz/gorse

Shape Representation

Learning Continuous Signed Distance Functions for Shape Representation
https://github.com/facebookresearch/DeepSDF

This repository contains the code for the paper “Occupancy Networks - Learning 3D Reconstruction in Function Space”
https://github.com/autonomousvision/occupancy_networks

3D Data

PyTorch3D is FAIR’s library of reusable components for deep learning with 3D data
https://github.com/facebookresearch/pytorch3d

Object Detection

Detectron2 is FAIR’s next-generation research platform for object detection and segmentation.
https://github.com/facebookresearch/detectron2

This project provides the implementation for DetNAS: Backbone Search for Object Detection.
https://github.com/megvii-model/DetNAS

Face Recognition

Deepfakes Software For All
https://github.com/deepfakes/faceswap

An open source library for face detection in images. The face detection speed can reach 1500FPS.
https://github.com/ShiqiYu/libfacedetection

DeepFaceLab is the leading software for creating deepfakes.
https://github.com/iperov/DeepFaceLab

Image Recognition

Deep learning model for recognizing puzzle patterns in The Witness.
https://github.com/wandb/witness
I trained a robot to play The Witness
https://www.wandb.com/articles/i-trained-a-robot-to-play-the-witness
Is a Realistic Honey Simulation Possible?
https://www.youtube.com/watch?v=7SM816P5G9s

Fake Detector

FaceForensics++: Learning to Detect Manipulated Facial Images
https://github.com/ondyari/FaceForensics
https://arxiv.org/pdf/1901.08971.pdf

CenterFace(size of 7.3MB) is a practical anchor-free face detection and alignment method for edge devices.
https://github.com/Star-Clouds/CenterFace

Image Augmentation

Image augmentation for machine learning experiments.
https://github.com/aleju/imgaug

Depth-Aware video frame INterpolation (DAIN)

Depth-Aware Video Frame Interpolation (CVPR 2019)
https://github.com/baowenbo/DAIN

Gesture Recognizer

Gesture recognition via CNN. Implemented in Keras + Tensorflow/Theano + OpenCV
https://github.com/asingh33/CNNGestureRecognizer

基于卷积神经网络的数字手势识别安卓APP，识别数字手势0-10（The number gestures recognition Android APP based on convolutional neural network(CNN), which can recognize the gestures corresponding number 0 to 10）
https://github.com/tz28/Chinese-number-gestures-recognition

Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture and Jester
https://github.com/ahmetgunduz/Real-time-GesRec

Image & Video Classification

An end-to-end PyTorch framework for image and video classification
https://github.com/facebookresearch/ClassyVision

Turi Create simplifies the development of custom machine learning models.
https://github.com/apple/turicreate

Image Generataion

Progressive Growing of GANs for Improved Quality, Stability, and Variation
https://github.com/tkarras/progressive_growing_of_gans

Hacking

A small course on exploiting and defending neural networks
https://github.com/Kayzaks/HackingNeuralNetworks

AI Path Tracer Denoiser

This project is to create a CUDA accelerated Deep learning approach to denoise renders from a path tracer
https://github.com/Black-Phoenix/Ai-Path-Tracer-Denoiser

Inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
https://github.com/vt-vl-lab/3d-photo-inpainting

NVIDIA Merlin is a framework for building high-performance, deep learning-based recommender systems.
https://developer.nvidia.com/nvidia-merlin
Announcing NVIDIA Merlin: An Application Framework for Deep Recommender Systems
https://devblogs.nvidia.com/announcing-nvidia-merlin-application-framework-for-deep-recommender-systems/

Pose Estimation

COCO-WholeBody dataset is the first large-scale benchmark for whole-body pose estimation.
https://github.com/jin-s13/COCO-WholeBody

GCN (Graph Convolutional Networks)

Graph Convolutional Networks in PyTorch
https://github.com/tkipf/pygcn

Graph Convolution Network for PyTorch
https://github.com/dragen1860/GCN-PyTorch

Hierarchical Task Network (HTN)

Hierarchical task network
https://en.wikipedia.org/wiki/Hierarchical_task_network

Data Loading

The NVIDIA Data Loading Library (DALI) is a GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
https://github.com/NVIDIA/DALI

Papers

Shape Representation

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
http://openaccess.thecvf.com/content_CVPR_2019/html/Park_DeepSDF_Learning_Continuous_Signed_Distance_Functions_for_Shape_Representation_CVPR_2019_paper.html

Occupancy Networks: Learning 3D Reconstruction in Function Space
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks

Physical Animation

Try W&B to track machine learning experiments and visualize results
https://www.wandb.com/papers
AI Learns To Compute Game Physics In Microseconds
https://www.youtube.com/watch?v=atcKO15YVD8

Hardware Architecture

Large-scale Deep Unsupervised Learning using Graphics Processors
http://robotics.stanford.edu/~ang/papers/icml09-LargeScaleUnsupervisedDeepLearningGPU.pdf

Fast Support Vector Machine Training and Classification on Graphics Processors
https://www2.eecs.berkeley.edu/Pubs/TechRpts/2008/EECS-2008-11.pdf

HeteroSpark: A Heterogeneous CPU/GPU Spark Platform for Machine Learning Algorithms
https://www.researchgate.net/profile/Peilong_Li/publication/282865411_HeteroSpark_A_Heterogeneous_CPUGPU_Spark_Platform_for_Machine_Learning_Algorithms/links/56205bd908aed8dd19404816/HeteroSpark-A-Heterogeneous-CPU-GPU-Spark-Platform-for-Machine-Learning-Algorithms.pdf

Transformations

Self-learning Transformations for Improving Gaze and Head Redirection
https://ait.ethz.ch/projects/2020/STED-gaze/
https://arxiv.org/abs/2010.12307
https://arxiv.org/pdf/2010.12307.pdf

3D Scenes

Pose2Room: Understanding 3D Scenes from Human Activities
https://yinyunie.github.io/pose2room-page/

Racing Game

Game AI: Simulating Car Racing Game by Applying Pathfinding Algorithms
http://www.ijmlc.org/papers/82-A1090.pdf

Reinforcement Learning for a Simple Racing Game
https://web.stanford.edu/class/aa228/reports/2018/final150.pdf

Blogs

Comprehensive

Research in human-centered AI, deep learning, autonomous vehicles & robotics at MIT and beyond.
https://lexfridman.com/

Math

Using neural networks to solve advanced mathematics equations
https://ai.facebook.com/blog/using-neural-networks-to-solve-advanced-mathematics-equations/

Tutorials

Youtube Tutorials

Neural Network Architectures
https://www.youtube.com/watch?v=oJNHXPs0XDk

MindsDB is a predictive AI layer for existing databases, making it easy for organizations to apply machine learning to their own data.
https://www.youtube.com/channel/UC5_wBOLCWath6q1iTgPPD5A
Machine Learning in one line of code
https://github.com/mindsdb/mindsdb

OpenAI Plays Hide and Seek…and Breaks The Game!
https://www.youtube.com/watch?v=Lu56xVlZ40M

Books

PyTorch

Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD 1st Edition (July 14, 2020)
https://www.amazon.com/Deep-Learning-Coders-fastai-PyTorch/dp/1492045527

Deep Learning with PyTorch 1st Edition (June 9, 2020)
https://www.amazon.com/Deep-Learning-PyTorch-Eli-Stevens/dp/1617295264

Commercial Product

Code Review

Write better code with the knowledge of the global development community.
https://www.deepcode.ai/

Voice

Instantly Transform Any Text Into A 100% Human-Sounding Voiceover with only 3 clicks!
https://speechelo.com/

Visual

An A.I. agent for visual tasks
https://deepai.org/zendo

Digital Creative

Runway is a new kind of creative suite. One where AI is a collaborator and anything you can imagine can be created.
https://runwayml.com/

Stable Diffusion is a deep learning, text-to-image model released in 2022. https://stability.ai/

Completions

AI Completions. Never Code Alone.
https://www.tabnine.com/

Social Accounts

Twitter Accounts

Research Scientist at @GoogleAI in the Brain Team. Deep Learning with Graphs.
https://twitter.com/thomaskipf

maths, visualisations, conversational AI. lead scientist @Poly_AI, previously @GoogleAI, PhD @Cambridge_Uni. living in Singapore.
https://twitter.com/matthen2

Dataset

Dance Motion

This repo contains starter code for using the AIST++ dataset.
https://github.com/google/aistplusplus_api
https://google.github.io/aistplusplus_dataset/

It was inevitable: the scent of bitter almonds always reminded him of the fate of unrequited love. ― Gabriel Garcia Marquez