You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Titung/urban-surveillance-mode-classifier

MLP classifier head trained on frozen YAMNet embeddings (Titung/urban-surveillance-yamnet-embeddings) for a personal safety wearable. Classes: ['Background', 'Car Crash', 'Glass Breaking', 'Gunshots', 'Screams', 'Siren', 'Tire Skidding', 'Vehicle Mechanical Sound']

Files

model.pt — TorchScript MLP, input: (batch, 1024) standardized YAMNet embedding
scaler.json — mean/scale for standardizing raw embeddings before inference
class_names.json — index-to-class-name mapping (model output order)
thresholds.json — per-class calibrated decision thresholds (validation-set calibrated)
alert_policy.json — per-mode (driving / trek / night_walk / standby) class thresholds
metrics.json — test macro-F1 and per-class test F1

Test performance

Macro-F1: 0.8019

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support