TensorFlow was developed for internal Google use in research and production. The initial version was released in November 2015. Then Google released the updated version of TensorFlow, named TensorFlow 2.0, in September 2019 with official inbuilt Keras support.

tensorflow

• https://www.tensorflow.org/tfx/serving/serving_basic
• https://www.geeksforgeeks.org/python-model-deployment-using-tensorflow-serving/
• https://levelup.gitconnected.com/using-tensorflow-with-flask-and-react-ba52babe4bb5

tensorflow-vs-pytorch

• https://medium.com/@ashishpaikray32/is-pytorch-better-than-tensorflow-e4f5a4c6569c
• https://medium.com/aimluae/tensorflow-vs-pytorch-which-will-be-the-top-deep-learning-framework-in-2022-a3488635029

PyTorch

• https://github.com/spinningideas/resources/wiki/PyTorch

Code

• https://www.tensorflow.org/js/
• https://github.com/tensorflow/tfjs
• https://www.tensorflow.org/js/demos
• JS TicTacToe + https://www.tensorflowtictactoe.co/
• Jupyter notebook
• https://github.com/jamesq9/Tic-Tac-Toe-Machine-Learning-Using-Reinforcement-Learning

Models

• https://github.com/tensorflow/tfjs-models
• https://tfhub.dev/
• Model Garden is a repository that makes the source code for SOTA models available.

Introductory Articles/Videos

• https://medium.com/@BhashkarKunal/image-classification-api-creation-using-tensorflow-flask-mongodb-61a53835e62d - Really Good
• https://towardsdatascience.com/easy-image-classification-with-tensorflow-2-0-f734fee52d13
• https://www.youtube.com/watch?v=N2DdsIe7TL0&list=PLCrXLkoWFdir9ir7GTiLhKVZse_ESWGvQ&index=8&t=63s
• https://www.dlighthouse.co/2019/04/tensorflow-keras-predict-house-prices-1-4.html
• https://blog.logrocket.com/tensorflow-js-an-intro-and-analysis-with-use-cases-8e1f9a973183/
• https://neptune.ai/blog/deep-dive-into-ml-models-in-production-using-tfx-and-kubeflow

Playground

• TensorFlow Playground is a small but polished educational tool for understanding the basics of neural networks. It offers a simple dense network visualized inside a clean UI.

Integrations

React

• https://github.com/joshuaellis/react-tensorflow - set of hooks to more easily integrate tensorflow into react apps

Keras

https://machinelearningmastery.com/display-deep-learning-model-training-history-in-keras/

Example Apps

• https://github.com/tensorflow/tfjs-examples
• https://www.dlighthouse.co/2020/02/creating-tensorflowjs-reactjs-js-app.html
• https://github.com/drginm/real-estate-tensorflow
• https://github.com/princefishthrower/react-speech-recognition-example
• https://rubikscode.net/2019/03/18/introduction-to-tensorflow-js-with-real-world-example/
• https://github.com/joshuaellis/react-tensorflow

Audio

• https://www.loginradius.com/blog/async/quick-look-at-react-speech-recognition/ + https://github.com/princefishthrower/react-speech-recognition-example

Vision/Object Detection

• https://github.com/nicknochnack/ReactComputerVisionTemplate && https://github.com/nicknochnack/RealTimeObjectDetectionTFJSReact
• https://github.com/tensorflow/tfjs/blob/master/tfjs-automl/demo/object_detection/index.js
• https://github.com/webrtcHacks/facetouchmonitor/blob/master/detect.js
• https://github.com/tensorflow/tfjs-models/tree/master/face-landmarks-detection
• https://medium.com/swlh/image-object-detection-tensorflow-2-object-detection-api-af7244d4c34e
• https://towardsdatascience.com/real-time-mobile-video-object-detection-using-tensorflow-a75fa0c5859d
• https://towardsdatascience.com/how-to-build-a-custom-object-detector-classifier-using-tensorflow-object-detection-api-811b7bcd31c4

Sentiment

• https://towardsdatascience.com/how-to-use-tensorflow-js-in-react-js-sentimental-analysis-59c538c07256 + https://github.com/manfye/tfjs-react

Chatbots

• https://www.codeproject.com/Articles/5282694/AI-Chatbots-With-TensorFlow-js-Creating-a-Movie-Di
• https://github.com/Machine-Learning-Tokyo/seq2seq_bot
• https://github.com/the-new-sky/Wisty.js

Voice

• https://github.com/CorentinJ/Real-Time-Voice-Cloning + https://github.com/CorentinJ/Real-Time-Voice-Cloning/issues/364

Training Models

• https://towardsdatascience.com/how-to-train-a-tensorflow-2-object-detection-model-25d4da64b817
• https://towardsdatascience.com/how-to-build-an-amazing-music-recommendation-system-4cce2719a572 + https://github.com/AmolMavuduru/SpotifyRecommenderSystem

Loading Models

• https://towardsdatascience.com/loading-models-into-tensorflow-js-using-react-js-f3e118ee4a59

Libraries

TensorFlow.js is a JavaScript library for Machine Learning that allows you to train and deploy models both in the browser and server-side with Node.js.

• ReactTensorFlow
• TensorFlow Serving is for deploying TensorFlow models on servers, be them in-house or on the cloud, and is used within the TensorFlow Extended (TFX) end-to-end Machine Learning platform. Serving makes it easy to serialize models into well-defined directories with model tags and select which model is used to make inference requests while keeping server architecture and APIs static.
• TensorFlow Extended is TensorFlow’s end-to-end platform for model deployment. You can load, validate, analyze, and transform data; train and evaluate models; deploy models using Serving or Lite, and then track artifacts and their dependencies.
• TensorFlow Lite (TFLite) is for use when deploying TensorFlow models on mobile or IoT/embedded devices. TFLite compresses and optimizes models for these devices, and more widely addresses 5 constraints for on-device Artificial Intelligence — latency, connectivity, privacy, size, and power consumption.
• Tensorflow Hubcontains TensorFlow, TensorFlow Lite, and TensorFlow.js models for different use cases, with models available for image, video, audio, and text problem domains. TensorFlow Cloud is a library that allows you to connect your local environment to Google Cloud.

Related Frameworks/Helpful Tools

• MediaPipe mework for building multimodal, cross-platform applied Machine Learning pipelines which can be used for face detection, multi-hand tracking, object detection, and more.

• Google Coral created to address local AI rather than cloud-based in many industries and is a complete toolkit to build products with local AI.

• Vertex AI Google Cloud’s unified Machine Learning platform. which is to unify services on GCP, AI Platform, and AutoML into one platform. Vertex AI can help you automate, monitor, and govern Machine Learning systems by orchestrating workflows in a serverless manner.