Experiment lab
Two ways to probe expression recognition
The teaching simulation uses fixed, published rules to show how conditions change a prediction — no camera, no upload, no model. The photo lab is different: it runs a real pre-trained expression model inside your browser on a photo you choose.
Real model, real inference. This tab runs a pre-trained facial-expression network inside your browser on a photo you choose. Nothing is uploaded. The teaching simulation in the other tab is a rule-based demo and is not used here — if inference fails, you will see the error, never a substituted fake result.
Drop a photo here, or choose one
JPG, PNG or WebP · up to 10 MB · single person
Please use your own photo, or one you have permission to use.
Model output
Choose a photo and press “Run analysis”. Results appear here.
This model classifies visible facial-expression patterns. It cannot determine how you actually feel. Scores are model outputs, not measured accuracy.
Your photo is processed in your browser and is not uploaded. The first use of this module downloads model files (about 0.9 MB). Photos and results are never written to storage and disappear when you clear them or close the page.