Deep Learning
Neural networks.
Contents
Courses
A free five-weekend plan to self-learners to learn the basics of deep-learning architectures like CNNs, LSTMs, RNNs, VAEs, GANs, DQN, A3C and more (2019)
A free deep reinforcement learning course by OpenAI (2019)
a 3-6 month Udacity nanodegree, spanning multiple courses (2018)
Table of Contents
Magenta is a project by Google exploring the role of machine learning in the process of creating art and music.
The CaffeNet model, a popular deep learning model for image classification. This is a PyTorch implementation.
Keras is a simple, modular, and extensible high-level Python API for deep learning.
Microsoft Cognitive Toolkit (CNTK) is an open-source deep-learning toolkit.
State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
Detectron2 is FAIR's next-generation library for object detection and segmentation.
PyTorch Image Models (timm) is a collection of pre-trained image classification models.
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
NeMo is a conversational AI toolkit built from the ground up for researchers and developers to create and experiment with the world's leading pre-trained conversational AI models.
High-resolution image synthesis with latent diffusion models
InvokeAI is a leading creative engine for Python, providing tools for AI-powered creativity.
StyleGAN3 is an efficient and high-fidelity generative adversarial network for image synthesis.
StyleGAN2 is an efficient and high-fidelity generative adversarial network for image synthesis.
FastText is a library for efficient learning of word representations and sentence classification.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Tutorials
Researchers
https://spandan-madan.github.io/DeepLearningProject/
https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/
Textual QA corpus from CNN and DailyMail. More than 300K documents in total. Paper for reference.
Open Images is a dataset of ~9 million URLs to images that have been annotated with labels spanning over 6000 categories.
MNIST like fashion product dataset consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes.
Contains about 10 million news articles classified using opensources.co types
15488 visible-infrared paired images (30976 images) for low-light vision research, Project_Page
Frameworks
a fast and flexible tool for deep learning on multi-GPU
Fast, flexible and fun neural networks.
Open source software library for numerical computation using data flow graphs
Microsoft Distributed Machine Learning Tookit
Simplified interface for TensorFlow (mimicking Scikit Learn)
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning framework
Samsung Distributed machine learning platform
A Minimalist GPU-only N-Dimensional ConvNets Framework
Amazon's library for building Deep Learning models
PArallel Distributed Deep LEarning by Baidu
a lightweight library to build and train neural networks in Theano
wrappers and abstractions around existing neural network libraries, most notably Lasagne
a library for constructing neural networks by Google's DeepMind
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Game agent framework: Use any video game as a deep learning sandbox
A New Lightweight, Modular, and Scalable Deep Learning Framework
Hardware-accelerated deep learning and linear algebra (NumPy) library for the web
A fast and framework agnostic image augmentation library
A general-purpose ML pipelining framework
High-level utils for PyTorch DL & RL research. It was developed with a focus on reproducibility, fast experimentation and code/ideas reusing
A toolkit for reproducible reinforcement learning research
Train and run object detection models with 5-10 lines of code
An unsupervised machine learning library for graph structured data
A lightweight library for neural networks that runs anywhere
A TensorFlow library for applied reinforcement learning
A Feature Store for ML and Data-Intensive AI
Representation learning on dynamic graphs
A computer vision framework for self-supervised learning
Deep Learning with Clear Code and Speed
a neural network ecosystem for JAX that is designed for flexibility
An Integrated Large-scale Model Training System with Efficient Parallelization Techniques
Application-oriented deep reinforcement learning framework addressing real-world decision problems.
Tools
Easy-to-use library to boost deep learning inference leveraging multiple deep learning compilers.
A little logger for machine learning research. Log any object to the console, CSVs, TensorBoard, text log files, and more with just one call to logger.log()
Miscellaneous
The original code from the DeepMind article + tweaks
Easy to install and use deep learning Faster R-CNN face detection for images and video in a docker container.
Curated list of articles related to deep learning scientific research applied to music
Curated list of articles related to deep learning scientific research on graph structured data at the graph level.
Curated list of articles related to deep learning scientific research on graph structured data at the node level.
contains examples, utilities and best practices for building recommendation systems. Implementations of several state-of-the-art algorithms are provided for self-study and customization in your own applications.