Edge Impulse Experts / Car Detection and Tracking Public
Target: Raspberry Pi 4 Clone this project

Test data

Set confidence 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.
Sample name Expected outcome Precision score Result
img_0047 car 89%
Show classification Show in data acquisition
img_0045 car 100%
Show classification Show in data acquisition
img_0029 car, car, car, car 100%
Show classification Show in data acquisition
img_0003 car 100%
Show classification Show in data acquisition
img_0117 car 100%
Show classification Show in data acquisition
img_0132 - 100%
Show classification Show in data acquisition
img_0129 car 100%
Show classification Show in data acquisition
img_0115 car 100%
Show classification Show in data acquisition
img_0082 car 100%
Show classification Show in data acquisition
img_0086 car, car 50%
Show classification Show in data acquisition
img_0023 car, car 92%
Show classification Show in data acquisition
img_0100 car, car, car 66%
Show classification Show in data acquisition
img_0073 car, car, car, car 100%
Show classification Show in data acquisition
img_0092 car, car, car 100%
Show classification Show in data acquisition
img_0095 car 100%
Show classification Show in data acquisition
img_0093 car, car, car, car 25%
Show classification Show in data acquisition
img_0077 car, car 0%
Show classification Show in data acquisition
img_0067 car, car, car 66%
Show classification Show in data acquisition
img_0052 car, car 50%
Show classification Show in data acquisition
img_0064 car, car, car 85%
Show classification Show in data acquisition
img_0066 car, car, car 100%
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
60.00%

Metrics for Object detection

Metric Value
mAP 0.55
mAP@[IoU=50] 0.75
mAP@[IoU=75] 0.66
mAP@[area=small] 0.16
mAP@[area=medium] 0.66
mAP@[area=large] 0.85
Recall@[max_detections=1] 0.24
Recall@[max_detections=10] 0.59
Recall@[max_detections=100] 0.59
Recall@[area=small] 0.18
Recall@[area=medium] 0.72
Recall@[area=large] 0.88

Confusion matrix

Precision scoreuncertain
Precision score--
f1 score0.00

Feature explorer

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