Product recognition demo for supermarket shelf images
Find a file
tngo 7fff0cf724 docs: record the live pacing dependence and the new test coverage
The live label count is a function of frame pacing, not a fixed property: a
track needs two attempts to settle, so pushing frames faster than the classifier
drains them reports fewer labels (12/8/2/6 at full speed on the same clip, 14
paced, 38 of 30 frames). Precision stays 100% and 0 unknowns are accepted at
every pacing. Also records the local-scale and DecisionPolicy tests.
2026-09-28 22:41:39 +09:00
.github/workflows chore: run the Python suite from the repository root 2026-09-28 17:26:58 +09:00
recognization docs: record the live pacing dependence and the new test coverage 2026-09-28 22:41:39 +09:00
.gitignore Initial commit for push folder 2026-09-18 09:13:53 +09:00