https://github.com/trixky/fashion_cnn
An online convolutional neural network (CNN) model for classifying fashion items.
https://github.com/trixky/fashion_cnn
classification-model convolutional-neural-network mlp mnist mnist-fashion multilayer-perceptron tensorflow tensorflowjs
Last synced: over 1 year ago
JSON representation
An online convolutional neural network (CNN) model for classifying fashion items.
- Host: GitHub
- URL: https://github.com/trixky/fashion_cnn
- Owner: trixky
- Created: 2024-07-07T11:31:15.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-07-07T13:51:38.000Z (almost 2 years ago)
- Last Synced: 2025-01-23T23:53:33.229Z (over 1 year ago)
- Topics: classification-model, convolutional-neural-network, mlp, mnist, mnist-fashion, multilayer-perceptron, tensorflow, tensorflowjs
- Language: Svelte
- Homepage: https://trixky.github.io/fashion_cnn/
- Size: 14.2 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# fashion_cnn
An [online](https://trixky.github.io/fashion_cnn/) [convolutional neural network](https://en.wikipedia.org/wiki/Convolutional_neural_network) (CNN) model for classifying fashion items.
The model is trained on the [MNIST fashion dataset](https://www.tensorflow.org/datasets/catalog/fashion_mnist) and implemented using the [TensorFlow.js](https://www.tensorflow.org/js) library.
> The model is loaded on the client side and all calculations are made on the device.
## Setup
```bash
npm run install
npm run dev #localhost:5173
```
## Model caracteristics
- dataset: MNIST (fashion) (10 000 samples)
- input layer: 784 (28x28 pixels)
- convolutional layers (4):
* 16(28x28)[5x5 filter] + stride[2] & max pool[2x2]
* 32(14x14)[5x5 filter] + stride[2] & max pool[2x2]
- hidden layers (1): 128 neurons (ReLU activation)
- output layer: 10 (Softmax activation)
- optimizer: Adam
- loss: categoricalCrossentropy
- metrics: accuracy
- epochs: 10
- batch size: 512