TensorFlow is an open source software library for numerical computation utilizing data flow graphs. The graph nodes speak to mathematical operations, while the graph edges speak to the multidimensional data arrays (tensors) that flow between them. This adaptable architecture gives you a chance to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code. TensorFlow also includes TensorBoard, a data visualization toolkit.
TensorFlow was initially created by researchers and engineers working on the Google Brain team inside Google’s Machine Intelligence Research organization for the reasons of conducting machine learning and deep neural networks research. The system is sufficiently general to be applicable in a wide assortment of other domains, as well.
Watch this below around 2 hours video TensorFlow and Deep Learning – without a PhD.
Below are some of the Ultimate Collection List of Tensor Flow resources gathered with a good portion of tutorials and online courses that can help you to Self-study TensorFlow framework on your own! Please feel free to suggest more materials in the comments!
- Getting Started with TensorFlow by Giancarlo Zaccone
- First Contact with TensorFlow by Jordi Torres, professor at UPC Barcelona Tech and a research manager and senior advisor at Barcelona Supercomputing Center
- Deep Learning with Python – Develop Deep Learning Models on Theano and TensorFlow Using Keras by Jason Brownlee
- TensorFlow Guide 1 – A guide to installation and use
- TensorFlow Guide 2 – Continuation of first video
- TensorFlow Basic Usage – A guide going over basic usage
- Some useful TensorFlow related videos on YouTube – Must Watch
- TensorFlow Deep MNIST for Experts – Goes over Deep MNIST
- TensorFlow Udacity Deep Learning – Basic steps to install TensorFlow for free on the Cloud 9 online service with 1Gb of data
- Why Google wants everyone to have access to TensorFlow
- Videos from TensorFlow Silicon Valley Meet Up 1/19/2016
- Videos from TensorFlow Silicon Valley Meet Up 1/21/2016
- Stanford CS224d Lecture 7 – Introduction to TensorFlow, 19th Apr 2016 – CS224d Deep Learning for Natural Language Processing by Richard Socher
- Diving into Machine Learning through TensorFlow – Pycon 2016 Portland Oregon, Slide& Code by Julia Ferraioli, Amy Unruh, Eli Bixby
- TensorFlow in 5 Minutes
- Large Scale Deep Learning with TensorFlow – Spark Summit 2016 Keynote by Jeff Dean
- Scikit Flow (TF Learn) – Simplified interface for Deep/Machine Learning (now part of TensorFlow)
- tflearn – Deep learning library featuring a higher-level API
- TensorFlow-Slim – High-level library for defining models
- TensorFrames – TensorFlow binding for Apache Spark
- caffe-tensorflow – Convert Caffe models to TensorFlow format
- keras – Minimal, modular deep learning library for TensorFlow and Theano
- SyntaxNet: Neural Models of Syntax – A TensorFlow implementation of the models described in Globally Normalized Transition-Based Neural Networks, Andor et al. (2016)
- TensorFlow Tutorial 1 – From the basics to slightly more interesting applications of TensorFlow
- TensorFlow Tutorial 2 – Introduction to deep learning based on Google’s TensorFlow framework. These tutorials are direct ports of Newmu’s Theano
- TensorFlow Examples – TensorFlow tutorials and code examples for beginners
- Sungjoon’s TensorFlow-101 – TensorFlow tutorials written in Python with Jupyter Notebook
- Terry Um’s TensorFlow Exercises – Re-create the codes from other TensorFlow examples
- Installing TensorFlow on Raspberry Pi 3 – TensorFlow compiled and running properly on the Raspberry Pi
- Pretty Tensor – Pretty Tensor provides a high level builder API
- Neural Style – An implementation of neural style
- TensorFlow White Paper Notes – Annotated notes and summaries of the TensorFlow white paper, along with SVG figures and links to documentation
- NeuralArt – Implementation of A Neural Algorithm of Artistic Style
- Deep-Q learning Pong with TensorFlow and PyGame
- Generative Handwriting Demo using TensorFlow – An attempt to implement the random handwriting generation portion of Alex Graves’ paper
- Neural Turing Machine in TensorFlow – implementation of Neural Turing Machine
- GoogleNet Convolutional Neural Network Groups Movie Scenes By Setting – Search, filter, and describe videos based on objects, places, and other things that appear in them
- Neural machine translation between the writings of Shakespeare and modern English using TensorFlow – This performs a monolingual translation, going from modern English to Shakespeare and vis-versa.
- Colornet – Neural Network to colorize grayscale images – Neural Network to colorize grayscale images
- Neural Caption Generator – Implementation of “Show and Tell”
- Neural Caption Generator with Attention – Implementation of “Show, Attend and Tell”
- Weakly_detector – Implementation of “Learning Deep Features for Discriminative Localization”
- Dynamic Capacity Networks – Implementation of “Dynamic Capacity Networks”
- HMM in TensorFlow – Implementation of viterbi and forward/backward algorithms for HMM
- DeepOSM – Train TensorFlow neural nets with OpenStreetMap features and satellite imagery.
- DQN-tensorflow – Tensorflow implementation of DeepMind’s ‘Human-Level Control through Deep Reinforcement Learning’ with OpenAI Gym by Devsisters.com
- Highway Network – Tensorflow implementation of “Training Very Deep Networks” with a blog post
- Sentence Classification with CNN – Tensorflow implementation of “Convolutional Neural Networks for Sentence Classification” with a blog post
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems – This paper describes the TensorFlow interface and an implementation of that interface that we have built at Google
- Comparative Study of Deep Learning Software Frameworks – The study is performed on several types of deep learning architectures and we evaluate the performance of the above frameworks when employed on a single machine for both (multi-threaded) CPU and GPU (Nvidia Titan X) settings
- Distributed TensorFlow with MPI – In this paper, we extend recently proposed Google TensorFlow for execution on large scale clusters using Message Passing Interface (MPI)
- Globally Normalized Transition-Based Neural Networks – This paper describes the models behind SyntaxNet.
- TensorFlow: A system for large-scale machine learning – This paper describes the TensorFlow dataflow model in contrast to existing systems and demonstrate the compelling performance
BEST ARTICLES ON TENSORFLOW
- TensorFlow for Poets – Goes over the implementation of TensorFlow
- Why TensorFlow will change the Game for AI
- Introduction to Scikit Flow – Simplified Interface to TensorFlow – Key Features Illustrated
- Building Machine Learning Estimator in TensorFlow – Understanding the Internals of TensorFlow Learn Estimators
- The indico Machine Learning Team’s take on TensorFlow
- The Good, Bad, & Ugly of TensorFlow – A survey of six months rapid evolution (+ tips/hacks and code to fix the ugly stuff), Dan Kuster at Indico, May 9, 2016
- Fizz Buzz in TensorFlow – A joke by Joel Grus
- TensorFlow: smarter machine learning, for everyone – An introduction to TensorFlow
- Magenta – Research project to advance the state of the art in machine intelligence for music and art generation.
- YOLO TensorFlow – Implementation of ‘YOLO : Real-Time Object Detection’
OPEN-source neural network framework
Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source – Release of SyntaxNet, “an open-source neural network framework implemented in TensorFlow that provides a foundation for Natural Language Understanding systems.