https://github.com/bjorntheprogrammer/fashion
An example of training the fashion mnist dataset using tensorflow-js
https://github.com/bjorntheprogrammer/fashion
Last synced: 2 months ago
JSON representation
An example of training the fashion mnist dataset using tensorflow-js
- Host: GitHub
- URL: https://github.com/bjorntheprogrammer/fashion
- Owner: BjornTheProgrammer
- Created: 2024-04-20T07:44:16.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-21T23:20:46.000Z (about 2 years ago)
- Last Synced: 2025-05-12T13:04:00.043Z (about 1 year ago)
- Language: TypeScript
- Size: 51 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# TensorFlow.js Example
Simple handwritten digit recongition using TensorFlow.js.
## Setup
To install dependencies:
```bash
npm install
```
To convert the jpg files into a csv for the neural network. Really recommend checking out the process script in `./src/process.ts` to understand what is happening more!
```bash
npm run process
```
## Training the Model
To train the model:
```bash
npm run start
```
See the code being run in `./src/index.ts`
## So what's happening?
The model is being trained on the MNIST dataset, which is a dataset of 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images. These images are first converted into a single dimensional array with just the strength of the pixel being represented by a value between 0 and 255. The model is then trained on these images to predict the digit that the image represents.