PrintGuard 2.0 — ShuffleNetV2 + few-shot prototypical network, TFLite via LiteRT, ≈5 MB, runs unmodified in the browser (Pyodide) and on CPython [P]
PrintGuard 2.0 is an updated system for detecting failures in 3D printing, utilizing a ShuffleNetV2 encoder and a prototypical network for few-shot fault detection. The new version features a significantly smaller TensorFlow Lite model, approximately 5 MB, which can run unmodified in both CPython and browser environments via Pyodide. This allows for flexible deployment and tuning of sensitivity and thresholds without retraining, with dynamic inference scheduling for fairness and efficiency. AI
IMPACT Enables efficient, on-device AI for specialized tasks like 3D printing fault detection.