Developer Relations / Audio Sensor Fusion - Step 1 Public
Clone this project

Test data

Set confidence thresholds
Model variants
Test 'Unoptimized (float32)' model Test 'Quantized (int8)' model
Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.
Sample name Expected outcome Length Accuracy Result
merged_data.s1.s6 extract 5s 100% 3 extract
Show classification Show in data acquisition
merged_data.s1.s5 pump 9s 100% 7 pump
Show classification Show in data acquisition
merged_data.s1.s4 pump 2s 100% 1 pump
Show classification Show in data acquisition
merged_data.s1.s3 idle 10s 100% 8 idle
Show classification Show in data acquisition
merged_data.s1.s2 extract 5s 67% 2 extract, 1 uncertain
Show classification Show in data acquisition
merged_data.s1.s1 grind 6s 100% 4 grind
Show classification Show in data acquisition
merged_data.s1 41s 14 pump, 13 idle, 7 extract, 4 grind, 1 uncertain
Show classification Show in data acquisition
merged_data.s1 41s 15 pump, 11 idle, 5 extract, 5 grind, 3 uncertain
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
96.15%

Feature explorer

Loading...
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy