AI & JavaScriptNo you’re not dreaming
View Slide
@yashintsOr is it?
Lead consultant @TelstraPurpleYaser Adel Mehraban@yashintsyashints.dev
Why do it in browser?Wide distributionInteractiveSensorsData stays on the client
@yashintshttps://playground.tensorflow.org
@yashintsTensorflow.js
@yashintsAllows inference andtraining entirely in thebrowser or Node.jsReleased March 2018 GPU-accelerated viaWebGLTensorFlow.js
@yashintsBuild your ownRun existingmodelsRetrainwith transfer learning
@yashintsTF TPUTF GPUCore APIWebGLLayers APIModelBrowser Node.jsTF CPUKeras ModelTensorflowSaved models
@yashintsPre-trained modelshttps://github.com/tensorflow/tfjs-models• MobileNet Object detection• PoseNet Human pose detection• CocoSSD Object localisation• BodyPix Human segmentation• USE Text classification
@yashintsBrowser examples
@yashintsBodyPixdemo
@yashints
@yashintsCreatabilityyas.fyi/2Zl4N2p
@yashintsAirbnb
@yashintsSpeech command
@yashintsaijs.rocksAsim Hussain � @jawache
@yashintsNode.js & Desktop
@yashintsyas.fyi/2LUfBkXMagenta Studio
@yashintsRetraining in Node.js
@yashintsDemo
@yashints“With Tensorflow.js and web,possibilities are endless, webdevelopment doesn’t have to beboring”“
@yashintsReferenceshttps://www.tensorflow.org/jshttps://github.com/tensorflow/tfjs-exampleshttps://www.freecodecamp.org/news/tensorflowjs-full-course/https://codelabs.developers.google.com/https://yashints.dev/blog/2018/11/27/get-started-with-tensorflowjsSlides https://yas.fyi/2MxNh7z
Reach outThanks!@yashintsyashints.dev