https://github.com/andrewjbateman/tensorflow-notepad

:clipboard: Notepad to create code for learning tensorFlow
https://github.com/andrewjbateman/tensorflow-notepad

javascript lodash nodejs tensorflow-js tensorflow-tutorials udemycourse visual-studio-code

Last synced: about 2 months ago
JSON representation

:clipboard: Notepad to create code for learning tensorFlow

• Host: GitHub
• URL: https://github.com/andrewjbateman/tensorflow-notepad
• Owner: AndrewJBateman
• Created: 2018-12-26T16:00:59.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2022-04-09T23:08:47.000Z (over 2 years ago)
• Last Synced: 2023-03-02T09:37:26.135Z (almost 2 years ago)
• Topics: javascript, lodash, nodejs, tensorflow-js, tensorflow-tutorials, udemycourse, visual-studio-code
• Language: JavaScript
• Homepage:
• Size: 792 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# :zap: TensorFlow Notepad

* Code to experiment with machine learning, shuffling data using a seed phrase.

* Uses TensorFlow in javascript, following Udemy Course [Machine Learning With Javascript].

*** Note: to open web links in a new window use: _ctrl+click on link_**

## :page_facing_up: Table of contents

* [:zap: TensorFlow Notepad](#zap-tensorflow-notepad)

  * [:page_facing_up: Table of contents](#page_facing_up-table-of-contents)

  * [:books: General info](#books-general-info)

  * [:camera: Screenshots](#camera-screenshots)

  * [:signal_strength: Technologies](#signal_strength-technologies)

  * [:floppy_disk: Setup](#floppy_disk-setup)

  * [:computer: Code Examples](#computer-code-examples)

  * [:cool: Features](#cool-features)

  * [:clipboard: Status & To-Do List](#clipboard-status--to-do-list)

  * [:clap: Inspiration](#clap-inspiration)

  * [:envelope: Contact](#envelope-contact)

## :books: General info

* "_TensorFlow.js is an open-source hardware-accelerated JavaScript library for training and deploying machine learning models._"

## :camera: Screenshots

![Example screenshot](./img/.png)

## :signal_strength: Technologies

* [TensorFlow.js](https://js.tensorflow.org/), an open-source hardware-accelerated JavaScript library for training and deploying machine learning models.

* [@tensorflow/tfjs-node v2](https://www.npmjs.com/package/@tensorflow/tfjs-node).

* [node.js v12 LTS](https://nodejs.org)

* [Lodash v4](https://lodash.com/), a modern JavaScript utility library delivering modularity, performance & extras. It has lots of methods but is slow.

* [Javascript playground](https://stephengrider.github.io/JSPlaygrounds/), a sandbox for writing javascript code and seeing the result on the right.

## :floppy_disk: Setup

* type `node load-csv.js` in console terminal to see any console.logs.

* It was necessary to install Python on my PC for this to compile.

* Use 'chrome://inspect/#devices' in browser to run in Chrome developer tools.

## :computer: Code Examples

* result of typing: `node load-csv.js`

```javascript

Features [ [ 10, 20 ], [ 12, 22 ], [ 11, 21 ] ]

Labels [ [ 1 ], [ 1 ], [ 0 ] ]

testFeatures undefined

testLabels undefined

```

## :cool: Features

* to follow

## :clipboard: Status & To-Do List

* Status: returns Features and Labels but testFeatures and testLabels undefined - see Code Example

* To-Do: Run again and correct data.

## :clap: Inspiration

Code from Udemy Course [Machine Learning With Javascript](https://www.udemy.com/machine-learning-with-javascript/learn/lecture/12355012#overview) section 183, 184.

## :envelope: Contact

* Repo created by [ABateman](https://www.andrewbateman.org) - you are welcome to [send me a message](https://andrewbateman.org/contact)