Louis Moreau / Face detection - FOMO - Embedded Online Conference Public
Target: Arduino Portenta H7 (Cortex-M7 480MHz) Clone this project

Test data

Set 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 F1 score Result
37606.2u8dfoqp face
Show classification Show in data acquisition
37598.2u8dfo82 face
Show classification Show in data acquisition
37613.2u8dfqe5 face, face, face
Show classification Show in data acquisition
37616.2u8dfrpc face
Show classification Show in data acquisition
37572.2u8dfqph face
Show classification Show in data acquisition
37603.2u8dft0u face
Show classification Show in data acquisition
37618.2u8dfriq face, face, face
Show classification Show in data acquisition
37686.2u8dhb78 face, face
Show classification Show in data acquisition
37615.2u8dfsdv face, face, face
Show classification Show in data acquisition
37626.2u8dft6o face
Show classification Show in data acquisition
37619.2u8dftjk face, face
Show classification Show in data acquisition
37623.2u8dg01t face
Show classification Show in data acquisition
37612.2u8dfvr0 face
Show classification Show in data acquisition
37604.2u8dg07r face, face
Show classification Show in data acquisition
37609.2u8dg0hl face, face
Show classification Show in data acquisition
37631.2u8dg2va face, face
Show classification Show in data acquisition
37621.2u8dg6t6 face
Show classification Show in data acquisition
37617.2u8dg0j6 face, face, face
Show classification Show in data acquisition
37625.2u8dg46a face, face, face, face
Show classification Show in data acquisition
37633.2u8dg7sv face
Show classification Show in data acquisition
37630.2u8dg2ve face, face, face
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