Nick Bild / smart_smoke_alarm Public
Target: Cortex-M4F 80MHz 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
person.3 person 1s 100% 1 person
Show classification Show in data acquisition
person.11 person 1s 100% 1 person
Show classification Show in data acquisition
person.9 person 1s 100% 1 person
Show classification Show in data acquisition
person.14 person 1s 100% 1 person
Show classification Show in data acquisition
person.21 person 1s 100% 1 person
Show classification Show in data acquisition
person.32 person 1s 100% 1 person
Show classification Show in data acquisition
person.37 person 1s 100% 1 person
Show classification Show in data acquisition
person.46 person 1s 100% 1 person
Show classification Show in data acquisition
person.56 person 1s 100% 1 person
Show classification Show in data acquisition
person.57 person 1s 0% 1 uncertain
Show classification Show in data acquisition
person.54 person 1s 100% 1 person
Show classification Show in data acquisition
person.73 person 1s 100% 1 person
Show classification Show in data acquisition
person.71 person 1s 100% 1 person
Show classification Show in data acquisition
person.81 person 1s 100% 1 person
Show classification Show in data acquisition
person.88 person 1s 100% 1 person
Show classification Show in data acquisition
person.83 person 1s 100% 1 person
Show classification Show in data acquisition
person.90 person 1s 100% 1 person
Show classification Show in data acquisition
person.91 person 1s 100% 1 person
Show classification Show in data acquisition
person.97 person 1s 100% 1 person
Show classification Show in data acquisition
person.99 person 1s 100% 1 person
Show classification Show in data acquisition
person.102 person 1s 100% 1 person
Show classification Show in data acquisition
person.105 person 1s 100% 1 person
Show classification Show in data acquisition
person.116 person 1s 100% 1 person
Show classification Show in data acquisition
person.118 person 1s 100% 1 person
Show classification Show in data acquisition
person.125 person 1s 100% 1 person
Show classification Show in data acquisition
person.141 person 1s 100% 1 person
Show classification Show in data acquisition
person.129 person 1s 100% 1 person
Show classification Show in data acquisition
person.140 person 1s 100% 1 person
Show classification Show in data acquisition
person.159 person 1s 100% 1 person
Show classification Show in data acquisition
person.157 person 1s 100% 1 person
Show classification Show in data acquisition
person.162 person 1s 100% 1 person
Show classification Show in data acquisition
person.166 person 1s 100% 1 person
Show classification Show in data acquisition
person.181 person 1s 0% 1 uncertain
Show classification Show in data acquisition
person.173 person 1s 100% 1 person
Show classification Show in data acquisition
person.175 person 1s 100% 1 person
Show classification Show in data acquisition
person.178 person 1s 100% 1 person
Show classification Show in data acquisition
person.187 person 1s 100% 1 person
Show classification Show in data acquisition
person.182 person 1s 100% 1 person
Show classification Show in data acquisition
person.188 person 1s 100% 1 person
Show classification Show in data acquisition
empty.4 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.13 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.21 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.39 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.40 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.42 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.43 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.49 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.46 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.117 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.58 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.59 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.65 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.77 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.81 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.84 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.85 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.87 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.92 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.122 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.123 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.99 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.101 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.106 empty 1s 100% 1 empty
Show classification Show in data acquisition
empty.108 empty 1s 100% 1 empty
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
96.88%

Confusion matrix

Loading...

Feature explorer

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