awesome-google-colab

授权协议 Readme
开发语言 Python
所属分类 神经网络/人工智能、 机器学习/深度学习
软件类型 开源软件
地区 不详
投 递 者 芮承运
操作系统 跨平台
开源组织
适用人群 未知
 软件概览

Unofficial Google Colaboratory Notebook and Repository Gallery

Please contact me to take over and revamp this repo (it gets around 30k views and 200k clicks per year), I don't have time to update or maintain it - message 15/03/2021

A curated list of repositories with fully functional click-and-run colab notebooks with data, code and description. The code in these repositories are in Python unless otherwise stated.

To learn more about they whys and hows of Colab see this post. For a few tips and tricks see this post.

If you have just a single notebook to submit, use the website https://google-colab.com/, it is really easy, on the top right corner click 'submit +'. The earlier you post the more visibility you will get over time

Caution: This is a work in progress, please contribute by adding colab functionality to your own data science projects on github or requestion it from the authors.


If you want to contribute to this list (please do), send me a pull request or contact me @dereknow or on linkedin.Also, a listed repository should be fixed or removed:

  • if there are no data or descriptive text in the notebooks.
  • the code throws out errors.


Apart from the colab-enabled repositories listed below, you can also with a bit of work run github jupyter notebooks directly on Google Colaboratory using CPU/GPU/TPU runtimes by replacing https://github.com in the URL by https://colab.research.google.com/github/. No local installation of Python is required. Of course, these notebooks would have to be adapted to ingest the necessary data and modules.

Search for 'Colab' or the 'Open in Colab' Badge to Open the Colabotary Notebooks in Each Repository

Ten Favourite Colab Notebooks

For more see https://google-colab.com/

Repository Table of Contents

Course and Tutorial

  • Python Data Science Notebook - Python Data Science Handbook: full text in Jupyter Notebooks

  • ML and EDA - Functional, data science centric introduction to Python.

  • Python Business Analytics - Python solutions to solve practical business problems.

  • Deep Learning Examples - Try out deep learning models online on Google Colab

  • Hvass-Labs - TensorFlow Tutorials with YouTube Videos

  • MIT deep learning - Tutorials, assignments, and competitions for MIT Deep Learning related courses.

  • NLP Tutorial - Natural Language Processing Tutorial for Deep Learning Researchers

  • DeepSchool.io - Deep Learning tutorials in jupyter notebooks.

  • Deep NLP Course - A deep NLP Course

  • pyprobml - Python code for "Machine learning: a probabilistic perspective"

  • MIT 6.S191 - Lab Materials for MIT 6.S191: Introduction to Deep Learning

  • HSE NLP - Resources for "Natural Language Processing" Coursera course

  • Real Word NLP - Example code for "Real-World Natural Language Processing"

  • Notebooks - Machine learning notebooks in different subjects optimized to run in google collaboratory

Technologies

Text

  • BERT - TensorFlow code and pre-trained models for BERT

  • XLNet - XLNet: Generalized Autoregressive Pretraining for Language Understanding

  • DeepPavlov Tutorials - An open source library for deep learning end-to-end dialog systems and chatbots.

  • TF NLP - Projects, Practice, NLP, TensorFlow 2, Google Colab

  • SparkNLP - State of the Art Natural Language Processing

  • Deep Text Recognition - Text recognition (optical character recognition) with deep learning methods.

  • BERTScore - Automatic Evaluation Metric for Bert.

  • Text Summurisation - Multiple implementations for abstractive text summurization

  • GPT-2 Colab - Retrain gpt-2 in colab

Image

  • DeepFaceLab - DeepFaceLab is a tool that utilizes machine learning to replace faces in videos.

  • CycleGAN and PIX2PIX - Image-to-Image Translation in PyTorch

  • DeOldify - A Deep Learning based project for colorizing and restoring old images (and video!)

  • Detectron2 - Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

  • EfficientNet - PyTorch - A PyTorch implementation of EfficientNet

  • Faceswap GAN - A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

  • Neural Style Transfer - Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style"

  • Compare GAN - Compare GAN code

  • hmr - Project page for End-to-end Recovery of Human Shape and Pose

Voice

  • Spleeter - Deezer source separation library including pretrained models.

  • TTS - Deep learning for Text to Speech

Reinforcement Learning

  • Dopamine - Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

  • Sonnet - TensorFlow-based neural network library

  • OpenSpiel - Collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

  • TF Agents - TF-Agents is a library for Reinforcement Learning in TensorFlow

  • bsuite - Collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

  • TF Generative Models - mplementations of a number of generative models in Tensorflow

  • DQN to Rainbow - A step-by-step tutorial from DQN to Rainbow

Visualisation

  • Altair - Declarative statistical visualization library for Python

  • Altair Curriculum - A data visualization curriculum of interactive notebooks.

  • bertviz - Tool for visualizing attention in the Transformer model

  • TF Graphics - TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow

  • deepreplay - Generate visualizations as in my "Hyper-parameters in Action!"

Operational

  • PySyft - A library for encrypted, privacy preserving machine learning

  • Mindsdb - Framework to streamline use of neural networks

  • Ranking - Learning to Rank in TensorFlow

  • TensorNetwork - A library for easy and efficient manipulation of tensor networks.

  • JAX - Composable transformations of Python+NumPy programs

  • BentoML - A platform for serving and deploying machine learning models

Other

Applications

Finance

  • RLTrader - A cryptocurrency trading environment using deep reinforcement learning and OpenAI's gym

  • TF Quant Finance - High-performance TensorFlow library for quantitative finance.

  • TensorTrade - An open source reinforcement learning framework for robust trading agents

Artistic

  • Rapping NN - Rap song writing recurrent neural network trained on Kanye West's entire discography

  • dl4g - Deep Learning for Graphics

Medical

  • DocProduct - Medical Q&A with Deep Language Models

Operations

  • 谷歌 colab For those who do not have access to the GPT-3 API it is important to remember we can still experiment with and use GPT-2! 对于那些无法访问GPT-3 API的人,请务必记住我们仍然可以尝试并使用GPT-2! For everyone who is not fa

  • 本文很多是对于 Colab 官方 Welcome 系列的总结,更多人工智能与深度学习相关知识参考人工智能与深度学习实战 https://github.com/wx-chevalier/AIDL-Series 系列文章。 Colaboratory Colaboratory 是一个免费的 Jupyter 笔记本环境,不需要进行任何设置就可以使用,并且完全在云端运行。借助 Colaboratory,我们

  • 1 - MLCC 通过机器学习,可以有效地解读数据的潜在含义,甚至可以改变思考问题的方式,使用统计信息而非逻辑推理来处理问题。 Google的机器学习速成课程(MLCC,machine-learning crash-course):https://developers.google.com/machine-learning/crash-course/ 支持多语言,共25节课程,包含40多项练习,有

 相关资料
  • 我有一个问题,在使用字体可怕的整个应用程序引擎。 通过Google Chrome开发者控制台,我发现以下错误: 资源被解释为字体,但使用MIME类型文本/html传输:“http://localhost:8080/wp-内容/插件/js\U composer/资产/库/字体awesome/字体/字体awesome webfont。woff/?v=4.2.0“。资源解释为字体,但使用MIME类型文本

  • Awesome Awesome Node.js A curated list of awesome lists that are about or related to Node.js. Inspired by the awesome list thing, going deeper down the rabbit hole. �� Meta stuff about this awesome li

  • A curated list of awesome things related to Vite.js This awesome list is for Vite 2.x and onward. Vite 1.x's list is archived. Resources Official Resources 文档 GitHub Repo Release Notes Vue 3 Docs Awes

  • Awesome Python 是一个资源整理集合,由 vinta 发起和维护。内容包括:Web框架、网络爬虫、网络内容提取、模板引擎、数据库、数据可视化、图片处理、文本处理、自然语言处理、机器学习、日志、代码分析等。 这个系列没有推荐 Python 书籍、经典博文、交互教程,所以另外推荐:《25本免费的Python电子书》、《学习Python编程的11个(教程)资源》、《PythonMonk:Py

  • Font Awesome 是一个图标工具包。其已经被重新设计并从头构建。除此之外,还增加了一些功能,比如 icon font ligature、SVG 框架、流行的前端库(如 React)的官方 NPM 包,以及对新 CDN 的访问。Font Awesome 已扩展至 7,865 个图标。

  • awesome-android 收录了来自 github 或其他网站的关于 Android 的大部分库。