컬렉션을 사용해 정리하기
내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.
아래의 학습 자료를 시작하기 전에 다음과 같은 조건을 갖춰야 합니다.
-
HTML, CSS, 자바스크립트를 사용하는 브라우저 프로그래밍에 익숙합니다.
-
Node.js 스크립트를 실행하는 명령줄을 능숙하게 사용합니다.
이 커리큘럼은 다음 작업을 원하는 사용자를 대상으로 합니다.
-
자바스크립트로 ML 모델 빌드
-
자바스크립트를 실행할 수 있는 모든 곳에서 기존 모델 실행
-
ML 모델을 웹브라우저로 배포
TensorFlow.js를 사용하면 자바스크립트로 ML 모델을 개발하거나 실행하고 클라이언트 측, 서버 측(Node.js 활용), 모바일 네이티브(React Native 활용), 데스크톱 네이티브(Electron 활용), IoT 기기(Raspberry Pi에서 Node.js 활용)에서도 브라우저에서 바로 ML을 사용할 수 있습니다. TensorFlow.js와 그 용도를 자세히 알아보려면 Google I/O에서 진행되었던 이 강연을 확인해 보세요.
3단계: TensorFlow.js를 사용한 예제로 연습하기
TensorFlow.js로 빌드된 예제
TensorFlow.js로 구현된 예시 집합이 포함되어 있는 GitHub 저장소입니다. 각 예시 디렉터리는 독립형이므로 디렉터리를 다른 프로젝트에 복사할 수 있습니다.
[null,null,[],[],[],null,["# Basics of TensorFlow for JavaScript development\n\n[TensorFlow](/tutorials) › [Resources](/resources/models-datasets) › [Learn ML](/resources/learn-ml) › [Guide](/resources/learn-ml/basics-of-tensorflow-for-js-development) › \n\nTensorFlow for JavaScript development\n=====================================\n\nBefore starting on the learning materials below, you should:\n\n1. Be comfortable with browser programming using HTML, CSS, \\& JavaScript\n\n2. Be familiar with using the command line to run Node.js scripts\n\nThis curriculum is for people who want to:\n\n1. Build ML models in JavaScript\n\n2. Run existing models anywhere Javascript can run\n\n3. Deploy ML models to web browsers\n\nTensorFlow.js lets you develop or execute ML models in JavaScript, and use ML directly in the browser client side, server side via Node.js, mobile native via React Native, desktop native via Electron, and even on IoT devices via Node.js on Raspberry Pi. To learn more about TensorFlow.js, and what can be done with it, check out [this talk](https://www.youtube.com/watch?v=uU-u-5Eo65g) at Google I/O. \n\nStep 1: Get introduced to machine learning in the browser\n---------------------------------------------------------\n\nTo get a quick introduction on basics for ML in JavaScript, take the self-paced [course on Edx](https://www.edx.org/course/google-ai-for-javascript-developers-with-tensorflowjs) or watch the videos below that take you from first principles, to using existing pre-made models, and even building your own neural network for classification. You can also try the [Make a smart webcam in JavaScript](https://codelabs.developers.google.com/codelabs/tensorflowjs-object-detection#0) Codelab for an interactive walkthrough of these concepts. \n\nSuperpowers for next gen web apps: Machine Learning \nThis high level intro to machine learning in JavaScript is for web developers looking to take their first steps with TensorFlow.js. \nFree\nWatch video\n\nCode \nTheory \n*close* \n[Google AI for JavaScript developers with TensorFlow.js](https://www.edx.org/course/google-ai-for-javascript-developers-with-tensorflowjs) \nGo from zero to hero with web ML using TensorFlow.js. Learn how to create next generation web apps that can run client side and be used on almost any device. \nFree [View course](https://www.edx.org/course/google-ai-for-javascript-developers-with-tensorflowjs) \nBuild \nCode \nTheory \nBuild \n[Make a smart webcam in JavaScript with a pre-trained model](https://codelabs.developers.google.com/codelabs/tensorflowjs-object-detection#0) \nLearn how to load and use one of the TensorFlow.js pre-trained models (COCO-SSD) and use it to recognize common objects it's been trained on. \nFree [See Codelab](https://codelabs.developers.google.com/codelabs/tensorflowjs-object-detection#0) \nTheory \nBuild \n\nStep 2: Dive deeper into Deep Learning\n--------------------------------------\n\nTo get a deeper understanding of how neural networks work, and a broader understanding of how to apply them to different problems, we have two books available.\n\n[Learning TensorFlow.js](https://www.oreilly.com/library/view/learning-tensorflowjs/9781492090786/) is a great place to start if you are new to Tensors and Machine Learning generally but have a good understanding of JavaScript. This book takes you all the way from the basics such as understanding how to manipulate data into Tensors, to quickly progressing to real world applications. After reading, you will understand how to load existing models, pass data to them, and interpret data that comes out.\n\n[Deep Learning with JavaScript](https://www.manning.com/books/deep-learning-with-javascript) is also a great place to start. It is accompanied by a large number of examples from GitHub so you can practice working with machine learning in JavaScript.\n\nThis book will demonstrate how to use a wide variety of neural network architectures, such as Convolutional Neural Networks, Recurrent Neural Networks, and advanced training paradigms such as reinforcement learning. It also provides clear explanations of what is actually happening with the neural network in the training process. \n[Learning TensorFlow.js](https://www.oreilly.com/library/view/learning-tensorflowjs/9781492090786/) \nby Gant Laborde \nA hands-on end-to-end approach to TensorFlow.js fundamentals for a broad technical audience. Once you finish this book, you'll know how to build and deploy production-ready deep learning systems with TensorFlow.js. \n[View book](https://www.oreilly.com/library/view/learning-tensorflowjs/9781492090786/) \nCode \nTheory \nBuild \n[Deep Learning with JavaScript](https://www.manning.com/books/deep-learning-with-javascript) \nby Shanqing Cai, Stanley Bileschi, Eric D. Nielsen with Francois Chollet \nWritten by the main authors of the TensorFlow library, this book provides fascinating use cases and in-depth instruction for deep learning apps in JavaScript in your browser or on Node. \n[View book](https://www.manning.com/books/deep-learning-with-javascript) \nCode \nTheory \nBuild \n\nStep 3: Practice with examples using TensorFlow.js\n--------------------------------------------------\n\nPractice makes perfect, and getting hands on experience is the best way to lock in the concepts. Check out the [TensorFlow.js](https://codelabs.developers.google.com/s/results?q=tensorflow.js) codelabs to further your knowledge with these step by step guides for common use cases:\n\n1. [Make your very own \"Teachable Machine\" from a blank canvas](https://codelabs.developers.google.com/codelabs/tensorflowjs-teachablemachine-codelab#0)\n\n2. [Handwritten digit recognition with Convolutional Neural Networks](https://codelabs.developers.google.com/codelabs/tfjs-training-classfication#0)\n\n3. [Make predictions from 2D data](https://codelabs.developers.google.com/codelabs/tfjs-training-regression#0)\n\n4. [Convert a Python SavedModel to TensorFlow.js format](https://codelabs.developers.google.com/codelabs/tensorflowjs-convert-python-savedmodel#0)\n\n5. [Use Firebase to deploy and host a TensorFlow.js model](https://codelabs.developers.google.com/codelabs/tensorflowjs-firebase-hosting-model#0)\n\n6. [Build a comment spam detection system](https://codelabs.developers.google.com/codelabs/tensorflowjs-comment-spam-detection#0)\n\n7. [Retrain a comment spam detection model to handle custom edge cases](https://codelabs.developers.google.com/tensorflow-retraining-comment-spam-detection#0)\n\n8. [Audio recognition using transfer learning](https://codelabs.developers.google.com/codelabs/tensorflowjs-audio-codelab#0)\n\nWith your knowledge of neural networks, you can more easily explore the [open sourced examples](https://github.com/tensorflow/tfjs-examples) created by the TensorFlow team. They are all [available on GitHub](https://github.com/tensorflow/tfjs-examples), so you can delve into the code and see how they work. \n[Examples built with TensorFlow.js](https://github.com/tensorflow/tfjs-examples) \nA repository on GitHub that contains a set of examples implemented in TensorFlow.js. Each example directory is standalone so the directory can be copied to another project. \nFree [Learn more](https://github.com/tensorflow/tfjs-examples) \nCode \nBuild \n[Explore our tutorials to learn how to get started with TensorFlow.js](/js/tutorials) \nThe TensorFlow tutorials are written as Jupyter notebooks and run directly in Google Colab---a hosted notebook environment that requires no setup. Click the Run in Google Colab button. \nFree [Learn more](/js/tutorials) \nCode \nBuild\n\nStep 4: Make something new!\n---------------------------\n\nOnce you've tested your knowledge, and practiced with some of the TensorFlow.js examples, you should be ready to start developing your own projects. Take a look at our [pretrained models](/js/models), and start building an app in minutes. Or you can train your own model using data you've collected, or by using public datasets. [Kaggle](https://www.kaggle.com/datasets) and [Google Dataset Search](https://toolbox.google.com/datasetsearch) are great places to find open datasets for training your model.\n\nIf you are looking for inspiration, check out our [Made With TensorFlow.js show and tell episodes](https://www.youtube.com/playlist?list=PLQY2H8rRoyvzSZZuF0qJpoJxZR1NgzcZw) from people all around the world who have used TensorFlow.js in their applications.\n\nYou can also see the latest contributions from the community by searching for the [#MadeWithTFJS](https://twitter.com/hashtag/MadeWithTFJS?src=hashtag_click&f=live) hashtag on social media. \n[Previous\nTheoretical and advanced machine learning with TensorFlow](/resources/learn-ml/theoretical-and-advanced-machine-learning) \n\nLearn, develop and build with TensorFlow\n----------------------------------------\n\n[Get started](/learn)"]]
