vietnh1009/QuickDraw

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1105 stars · 195 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python implementation of Google's Quick, Draw! game that recognizes hand-drawn sketches using a CNN trained on the Quick Draw dataset. It includes a webcam-based drawing app that tracks a colored pen and a canvas-based drawing app, plus training scripts and pretrained models for 20 categories.

Use cases

• recognize hand-drawn sketches with a neural network
• play a quick draw game using a webcam and a colored pen
• train a CNN on the Quick Draw dataset with custom categories
• classify doodles into 20 categories like apple, star, or tree
• experiment with PyTorch image classification on sketch data

When to choose

• you want a working sketch-recognition demo with pretrained models
• you want to learn CNN training with PyTorch and OpenCV on a fun dataset
• you want to retrain the classifier on your own set of Quick Draw categories

When to avoid

• you need production-grade sketch recognition with many categories
• you need a mobile or web deployment
• you need the full Quick Draw dataset coverage or stroke-based (sketchrnn) models

Facets

application · maturity maintenance

computer-vision image-processing machine-learning deep-learning computer-vision machine-learning deep-learning image-processing gaming-tools python cross-platform quickdraw sketch-classification cnn pytorch opencv webcam-drawing image-classification desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vietnh1009/QuickDraw")