Project library
Shape Classifier Demo
Draw a shape and see how a model classifies it.
STAR Summary
- Situation
- I wanted a model that can tell what shape someone drew.
- Task
- Build an interactive demo that classifies browser-drawn shapes into five supported QuickDraw categories.
- Action
-
- Used Google's QuickDraw sketches and built train/validation splits.
- Trained a small ResNet18 classifier in PyTorch.
- Deployed a CPU-only AWS Lambda endpoint so the browser can request predictions.
- Result
-
- Supports five QuickDraw classes—circle, triangle, square, hexagon, and octagon—but a held-out accuracy result has not yet been published.
- Predictions return quickly once the Lambda container is warm; cold starts can take longer.
Shape Classifier
Draw a circle, triangle, square, hexagon, or octagon to see the model's prediction.
Open full demo
Draw one of the supported shapes and let the model classify it.
- Draw on the canvas (circle, triangle, square, hexagon, or octagon).
- Click “Classify” to submit the drawing.
- Use the eraser button (or press C) to clear and try again.
- Review the confidence bar and per-shape scores on the right.
