Syntiant / Tutorial: Continuous motion recognition - RASynBoard 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
testing.4nkf19kl testing 2s
Show classification Show in data acquisition
testing.4nkf0okj testing 0s
Show classification Show in data acquisition
idle.3.cbor.1q53q9pm z_openset 10s
Show classification Show in data acquisition
updown.2.cbor.1q53q9pq updown 10s
Show classification Show in data acquisition
snake.1.cbor.1q53q9po snake 10s
Show classification Show in data acquisition
updown.3.cbor.1q53q9pt updown 10s
Show classification Show in data acquisition
wave.1.cbor.1q53q9pr wave 10s
Show classification Show in data acquisition
wave.2.cbor.1q53q9ps wave 10s
Show classification Show in data acquisition
snake.2.cbor.1q53q9pm snake 10s
Show classification Show in data acquisition
idle.2.cbor.1q53q9pg z_openset 10s
Show classification Show in data acquisition
updown.1.cbor.1q53q9pl updown 5s
Show classification Show in data acquisition
idle.4.cbor.1q53q9pj z_openset 10s
Show classification Show in data acquisition
wave.4.cbor.1q53q9pq wave 10s
Show classification Show in data acquisition
wave.3.cbor.1q53q9pt wave 10s
Show classification Show in data acquisition
idle.1.cbor.1q53q9pg z_openset 10s
Show classification Show in data acquisition
updown.4.cbor.1q53q9po updown 10s
Show classification Show in data acquisition
snake.3.cbor.1q53q9or snake 10s
Show classification Show in data acquisition

Model testing output

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