Edge Impulse Experts / Hand Gestures Public
Target: Raspberry Pi 5 Clone this project

Test data

Set thresholds
Model variants
No additional model variants available Test 'Unoptimized (float32)' 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
hand00066 five, neut 94%
Show classification Show in data acquisition Show in feature explorer
hand00065 five, neut 100%
Show classification Show in data acquisition Show in feature explorer
hand00092 five, five 89%
Show classification Show in data acquisition Show in feature explorer
hand00113 good, peace 94%
Show classification Show in data acquisition Show in feature explorer
hand00108 good, peace 89%
Show classification Show in data acquisition Show in feature explorer
hand00099 five, good 94%
Show classification Show in data acquisition Show in feature explorer
hand00095 five, good 94%
Show classification Show in data acquisition Show in feature explorer
hand00093 good, peace 94%
Show classification Show in data acquisition Show in feature explorer
hand00060 good, peace 100%
Show classification Show in data acquisition Show in feature explorer
hand00071 good, peace 100%
Show classification Show in data acquisition Show in feature explorer
hand00073 neut, peace 94%
Show classification Show in data acquisition Show in feature explorer
hand00014 five, good 100%
Show classification Show in data acquisition Show in feature explorer
hand00002 neut, neut 100%
Show classification Show in data acquisition Show in feature explorer
hand00012 five, good 94%
Show classification Show in data acquisition Show in feature explorer
hand00010 neut, peace 100%
Show classification Show in data acquisition Show in feature explorer
hand00023 neut, peace 100%
Show classification Show in data acquisition Show in feature explorer
hand00018 good, neut 94%
Show classification Show in data acquisition Show in feature explorer
hand00045 neut, peace 94%
Show classification Show in data acquisition Show in feature explorer
hand00068 five, peace 100%
Show classification Show in data acquisition Show in feature explorer
hand00082 five, neut 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 0.68
mAP@[IoU=50] 1.00
mAP@[IoU=75] 0.89
mAP@[area=small] -1.00
mAP@[area=medium] 0.70
mAP@[area=large] 0.67
Recall@[max_detections=1] 0.66
Recall@[max_detections=10] 0.70
Recall@[max_detections=100] 0.70
Recall@[area=small] -1.00
Recall@[area=medium] 0.72
Recall@[area=large] 0.68

Confusion matrix

Loading...

Feature explorer

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