DataHack Resources 2019

This is a list of resources for DataHack, and includes link to repositories and guides for machine learning and data science. Want to join DataHack 2019? Go to https://registration.datahack.org.il

General Resources 🤖

Blog Posts

• A Recipe for Training Neural Networks / Andrej Karpathy - Talks about common errors in training neural networks and how to avoid them.

Awesome Lists

• Awesome List of Deep Learning Project Ideas - Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas. Includes datasets
• Awesome Data Science - A repository to learn and apply data science in real world problems
• Awesome Data Visualizations
• Awesome Machine Learning

Repositories

• Tensor2Tensor GitHub repository - A library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research

Vision & Image 👁️ + 🖼️

Awesome Lists

• Awesome Vision - A curated list of awesome computer vision resources
• Awesome GAN Applications
• CycleGAN & Pix2Pix - Image-to-Image Translation in PyTorch. Software that can generate photos from paintings, turn horses into zebras, perform style transfer

Datasets

• http://www.cvpapers.com/datasets.html
• https://www.visualdata.io

NLP 💬

Awesome Lists

• Awesome NLP - 📖 A curated list of resources dedicated to Natural Language Processing (NLP)

Repositories

• Fairseq - A sequence modeling toolkit enabling training custom models for translation, summarization, language modeling and other text generation tasks. It provides reference implementations of various sequence-to-sequence models
• OpenAI GPT-2 - A really good pretrained language model (Code for the paper "Language Models are Unsupervised Multitask Learners")

Datasets

• https://github.com/niderhoff/nlp-datasets

Voice & Audio 📣

Blog Posts

Awesome Lists

• Awesome Deep Learning Music - Most links don't have code
• Awesome Audio Visualizations
• Awesome Speech Recognition and Speech Synthesis Papers - Note that these are academic papers

Repositories

Datasets

Tabular Data 📊

Blog Posts

Awesome Lists

Repositories

• XGBoost - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow

Datasets