Draw a digit from 0 to 9. A small convolutional network trained on the MNIST handwriting set reads it live, right in your browser.
Draw here
What the model sees: your drawing cropped, shrunk to fit a 20×20 box, and centered by mass in a 28×28 grid, the same way MNIST was prepared.
Prediction
Draw something to start.
Each stage below updates as you draw. Brighter cells mean stronger activation.
8 learned 5×5 filters slide over the image. Each one lights up where its pattern appears, such as a stroke at a certain angle.
28×28×8After max-pooling halves the size, 16 filters combine layer 1's maps into larger parts like loops, corners and line ends.
14×14×16The pooled maps are flattened to 784 numbers and mixed into 64 hidden units. Different digits light up different combinations.
6410 final scores pass through softmax and become the probabilities shown in the prediction panel.
10Messy or ambiguous drawings split the probability across look-alikes such as 4 and 9, or 3 and 5.