Edge Impulse Experts / Digital twin-enabled Smart Shipping Workstation Public
Target: Raspberry Pi 5 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
hammer_omniverse_sample_29 hammer 85%
Show classification Show in data acquisition
hammer_omniverse_sample_31 hammer 85%
Show classification Show in data acquisition
wrench_omniverse_sample_6 wrench 0%
Show classification Show in data acquisition
tea_cup_omniverse_sample_8 tea_cup 0%
Show classification Show in data acquisition
hammer_omniverse_test_sample_4 hammer 85%
Show classification Show in data acquisition
hammer_omniverse_test_sample_5 hammer 85%
Show classification Show in data acquisition
hammer_omniverse_sample_8 hammer 90%
Show classification Show in data acquisition
mouse_omniverse_sample_13 mouse 100%
Show classification Show in data acquisition
hammer_omniverse_sample_9 hammer 90%
Show classification Show in data acquisition
basketball_omniverse_sample_22 basketball 100%
Show classification Show in data acquisition
basketball_omniverse_sample_21 basketball 100%
Show classification Show in data acquisition
basketball_omniverse_sample_23 basketball 100%
Show classification Show in data acquisition
basketball_omniverse_sample_25 basketball 100%
Show classification Show in data acquisition
basketball_omniverse_sample_24 basketball 100%
Show classification Show in data acquisition
screwdriver_omniverse_test_sample_4 screwdriver 100%
Show classification Show in data acquisition
mouse_omniverse_test_sample_3 mouse 100%
Show classification Show in data acquisition
screwdriver_omniverse_test_sample_1 screwdriver 100%
Show classification Show in data acquisition
screwdriver_omniverse_test_sample_5 screwdriver 100%
Show classification Show in data acquisition
hammer_omniverse_test_sample_2 hammer 100%
Show classification Show in data acquisition
hammer_omniverse_test_sample_3 hammer 80%
Show classification Show in data acquisition
screwdriver_omniverse_test_sample_2 screwdriver 100%
Show classification Show in data acquisition
hammer_omniverse_test_sample_1 hammer 85%
Show classification Show in data acquisition
screwdriver_omniverse_sample_4 screwdriver 100%
Show classification Show in data acquisition
mouse_omniverse_sample_21 mouse 100%
Show classification Show in data acquisition
mouse_omniverse_sample_12 mouse 100%
Show classification Show in data acquisition
mouse_omniverse_sample_15 mouse 100%
Show classification Show in data acquisition
hammer_omniverse_sample_21 hammer 80%
Show classification Show in data acquisition
hammer_omniverse_sample_11 hammer 100%
Show classification Show in data acquisition
hammer_omniverse_sample_15 hammer 80%
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
93.10%

Metrics for Object detection

Metric Value
Precision (non-background) 0.83
Recall (non-background) 0.96
F1 Score (non-background) 0.89

Confusion matrix

Loading...

Feature explorer

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