Welcome to Colabverse
Home of the most interesting colab notebooks on the internet
The goal of this repository is to collect the most interesting colab notebooks in all fields. A combination of individual notebooks, textbooks, and courses are part of the list. Feel free to add more interesting colab notebooks. Or for any suggestions, reach out to me at misbah.sy(at)gmail.com
What is Colab?
Colaboratory is a free Jupyter notebook environment that requires no setup and runs entirely in the cloud.
With Colaboratory you can write and execute code, save and share your analyses, and access powerful computing resources, all for free from your browser.
Working with Notebooks in Colaboratory
- Overview of Colaboratory
- Guide to Markdown
- Importing libraries and installing dependencies
- Saving and loading notebooks in GitHub
- Interactive forms
- Interactive widgets
Working with Data
- Loading data: Drive, Sheets, and Google Cloud Storage
- Charts: visualizing data
- Getting started with BigQuery
Machine Learning Crash Course
These are a few of the notebooks from Google’s online Machine Learning course. See the full course website for more.
- Intro to Pandas
- Tensorflow concepts
- First steps with TensorFlow
- Intro to neural nets
- Intro to sparse data and embeddings
Using Accelerated Hardware
Colab Notebooks From Google Seedbank
- Lab 1: Loading and Understanding Your Data by Sally Goldman
- Lab 2: Training Your First TF Linear Regression Model by Sally Goldman
- Lab 3: Using Multiple Numerical Features and Feature Scaling by Sally Goldman
- Lab 4: Using Bucketized Numerical Features by Sally Goldman
- Lab 5: Using Categorical Features by Sally Goldman
- Lab 6: Creating Validation Data by Sally Goldman
- Lab 7: Feature Engineering - Creating Synthetic Features by Sally Goldman
- Lab 8: Training a Linear Classifier With Numerical and Categorical Features by Sally Goldman
-
Lab 9: Bucketized Features Using Quantiles and Feature Crosses by Sally Goldman
- Neural Translation with Attention
- Pix2Pix with Eager execution
- GAN Synth
- Fashion MNIST with Keras and TPUs
- Variational auto-encoder for music. by Adam Roberts and Jesse Engel
- GAN Synthesizer by Jesse Engel
- Neural Style Transfer with tf.keras
- Introduction to ML Fairness
- Convolutional VAE
- E-Z NSynth by Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Douglas Eck, Karen Simonyan, Mohammad Norouzi
- Performance RNN by Ian Simon, Sageev Oore, Curtis Hawthorne
- Spatial/Channel Attribution by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- Classifying Handwritten Digits
- Text generation using a RNN with eager execution
- Piano Transcription by Curtis Hawthorne, Erich Elsen, Jialin Song, Adam Roberts, Ian Simon, Colin Raffel, Jesse Engel, Sageev Oore, Douglas Eck
- Improving Neural Net Performance
- First Steps with TensorFlow
- 3D Style transfer
- AdaNet on TPU by Eugen Hotaj
- Semantic Dictionaries by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- Feature Inversion Caricatures with Lucid
- Explanations of black-box models with Shapley Values by Dimos Christopoulos
- Working with Tensors
- Dopamine: How to load and visualize the logs data produced by Dopamine. by Pablo Samuel Castro
- Activation Atlas by Shan Carter
- Logistic Regression
- Customizing AdaNet With TensorFlow Hub Modules by Tracy Cui
- TensorFlow Programming Concepts
- Colab GPU
- Part 1: The What-If Tool Comparing Two UCI Census Models
- Part 2: The What-If Tool Analyzing an Image Classifier
- Part 3: The What-If Tool Analyzing the COMPAS dataset
- Part 4: The What-If Tool Comparing Text Toxicity Classifiers
- Text classifier with TF-Hub
- Small Feature Sets
- Colab Widgets
- Generating semi-transparent Feature Visualizations by Alex Mordvintsev
- Synthetic Features and Outliers
- Mobile Net
- Predict House Prices with tf.keras
- Visualization Regularization by Chris Olah, Alexander Mordvintsev, Ludwig Schubert
- Post training optimization
- Part 1: Building a Classifier Model From Scratch
- Part 2: Improving the Model using Data Augmentation and Dropout
- Part 3: Feature Extraction and Fine tuning
- Formatting text in Colaboratory.
- AutoGraph: Easy control flow for graphs
- Classify movie reviews using tf.keras
- Use BigQuery in Colab
- Fashion MNIST with tf.keras
- CycleGAN: Unpaired Image to Image Translation by Parag K. Mital
- Pretrained Word Embeddings by Chris Boudreaux
- Sparsity and L1 Regularization
- Match images using DELF and TF-Hub
- Introduction to TensorFlow.js by Nikhil Thorat
- CharRNN by Chris Boudreaux
- Using OpenGL with Colab Cloud GPUs by Alexander Mordvintsev
- Conversation AI’s Pinned AUC Unintended Model Bias Demo by Lucas Dixon, John Li, Jeffrey Sorensen, Nithum Thain, Lucy Vasserman
- Tensorflow: Hello World
- TF-Hub Action Recognition Model
- Style Transfer
- Audio Style Transfer by Parag K. Mital
- Image Captioning with Attention with tf.keras and eager
- Unconditional Generative Models by Jesse Engel, Matthew Hoffman, Adam Roberts
- Teachable Machine by Nikhil Thorat
- Using Nucleus and TensorFlow for DNA Sequencing Error Correction by Gunjan Baid, Helen Li, Pi-Chuan Chang
- Teaching Machines to Draw by David Ha, Jonas Jongejan, Ian Johnson
- DeepDream by Alex Mordvintsev
- DCGAN with tf.keras and eager
- Feature Crosses
- Colab & Google Drive by Mike Tyka
- Compare GAN
- Tensor2Tensor: Translate from English to German with a pre-trained model by Łukasz Kaiser
- Train SketchRNN, convert to TF.js by David Ha
- Generate Shakespeare using tf.keras
- Negative Neurons - Feature Visualization by Chris Olah, Alexander Mordvintsev, Ludwig Schubert
- Dopamine: How to create and train a custom agent by Pablo Samuel Castro
- 3D Feature Visualization by Alex Mordvintsev
- Generative Adversarial Network (GAN)
- Neuron Groups by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- Lucid Modelzoo
- Data I/O in Colab
- Fibonacci Number generator and Conway’s game of life using TF Autograph.
- Universal Sentence Encoder
- Cloud TPU Template by Yu-Han Liu
- Categorize Iris flowers by species
- Lucid: A Quick Tutorial by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- Charts in Colab
- Intro to Neural Networks
- Colab basics: Cells
- Model Validation
- Aligned Feature Visualization Interpolation by Chris Olah, Alexander Mordvintsev, Ludwig Schubert
- Negative Neurons by Chris Olah, Alexander Mordvintsev, Ludwig Schubert
- Interaction Between Neurons by Chris Olah, Alexander Mordvintsev, Ludwig Schubert
- Activation Grid Visualizations by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- BigGAN
- Sparse Data and Embeddings
- Quick Introduction to pandas
- Build a linear model with Estimators
- Channel Attribution by Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, Alexander Mordvintsev
- Building a text classification model with TF Hub
- Mitigating Unwanted Biases by Andrew Zaldivar, Ben Hutchinson, Blake Lemoine, Brian Zhang, Margaret Mitchell
- Explore overfitting and underfitting
- Adversarial Interpretability Introduction
- xy2rgb.ipynb by Alexander Mordvintsev
- Dopamine: How to visualize Dopamine data in Tensorboard from Colab by Pablo Samuel Castro
- The AdaNet Algorithm by Charles Weill
Interesting Notebooks from ‘A gallery of interesting Jupyter Notebooks’
Programming and Computer Science
-
Automata and Computability using Jupyter, an entire course, based on forthcoming book published by Taylor and Francis; book title: “Automata and Computability: Programmer’s Perspective”, by Ganesh Gopalakrishnan, Professor, School of Computing, University of Utah, Salt Lake City. [in English, has Youtube videos]
-
Introduction to Programming (using Python), an entire introductory Python course written by Eric Matthes. This post explains the educational context in an Alaskan high school where Eric is a teacher.
- Numeric Computing is Fun A series of notebooks created to help educate aspiring computer programmers and data scientists of all ages with no previous programming experience.
Part 1: Introduction Part 2 : Prime Numbers Part 3 : Algorithms Overview Part 4: Automation Overview
- Understanding evolutionary strategies and covariance matrix adaptation, from the Advanced Evolutionary Computation: Theory and Practice course by Luis Martí. -Code Katas in Python, a collection of algorithmic and data structure exercises covering search and sorting algorithms, stacks, queues, linked lists, graphs, backtracking and greedy problems.
Statistics, Machine Learning and Data Science
- Python Data Science Handbook Supplemental Materials, a collection of notebooks by Jake VanderPlas to accompany the book.
Collection of material by John Wittenauer
Language
Libraries
Machine Learning Exercises
- Exercise 1 - Linear Regression
- Exercise 2 - Logistic Regression
- Exercise 3 - Multi-Class Classification
- Exercise 4 - Neural Networks
- Exercise 6 - Support Vector Machines
- Exercise 7 - K-Means Clustering & PCA
- Exercise 8 - Anomaly Detection & Recommendation Systems
Tensorflow Deep Learning Exercises
- Assignment 1 - Intro & Data Prep
- Assignment 2 - Regression & Neural Nets
- Assignment 3 - Regularization
- Assignment 4 - Convolutions
- Assignment 5 - Word Embeddings
- Assignment 6 - Recurrent Nets
Fast.ai Lessons
- Lesson 1 - Image Classification
- Lesson 2 - Multi-label Classification
- Lesson 3 - Structured And Time Series Data
- Lesson 4 - Sentiment Classification
- Lesson 5 - Recommendation Using Deep Learning
- Lesson 6 - Language Modeling With RNNs
- Lesson 7 - Convolutional Networks In Detail