digit_classifier

An online digit classifier using the multi-layer perceptrons (MLP) model.

The model is trained on the MNIST dataset and implemented using the TensorFlow.js library.

The model is loaded on the client side and all calculations are made on the device.

Setup

npm run install
npm run dev #localhost:5173

Model caracteristics

• dataset: MNIST (10 000 samples)
• input layer: 784 (28x28 pixels)
• hidden layers (2): 32 neurons (ReLU activation) + 16 neurons (ReLU activation)
• output layer: 10 (Softmax activation)
• optimizer: Adam
• loss: categoricalCrossentropy
• metrics: accuracy
• epochs: 50
• batch size: 512