Edge Impulse Experts / Face Detection Public
Target: Rubik Pi 3 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.

Apply filters

Sample name Expected outcome Precision score Result
face00014 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00045 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00004 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00064 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00060 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00028 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
face00015 face, face, face, face, face, face, face, face, face 100%
Show classification Show in data acquisition Show in feature explorer
Filter yielded no results, click to adjust the filter

Model testing output

Results

Model version:
Accuracy
100.00%

Metrics for Object detection

Metric Value
mAP 0.72
mAP@[IoU=50] 1.00
mAP@[IoU=75] 0.96
mAP@[area=small] -1.00
mAP@[area=medium] 0.72
mAP@[area=large] -1.00
Recall@[max_detections=1] 0.09
Recall@[max_detections=10] 0.76
Recall@[max_detections=100] 0.76
Recall@[area=small] -1.00
Recall@[area=medium] 0.76
Recall@[area=large] -1.00

Confusion matrix

Loading...

Feature explorer

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