tensor·factory

Live demo

The detector,
in your browser.

An 80 KB int8 ONNX model running on WebAssembly — the same model the CLI runs, no server and no upload. Your image never leaves the page.

loading model + sample…
Specimen · 480 × 480 pxFig. 01
Model
Verdict
Readout
box (norm)
box (px @480)
uint8
inference
How it works

The page loads a quantized ONNX model and runs it with onnxruntime-web (WebAssembly). The image is resized to 480 px, normalized, and fed to the net; the soft-argmax head returns a normalized xyxy box, quantized to four uint8 values — the whole detection contract. The Mock model is matched to the bundled synthetic sample; switch to Presence (the real-data model, reports present / absent) and Upload a microscope photo of a threaded insert to try it.

Prev← Python API SourceGitHub →