SolutionsExamples / pet_detection Public
Target: Qualcomm Dragonwing RB3 Gen 2 Development Kit Clone this project

Object detection settings

Switch to Keras (expert) mode Switch to visual (simple) mode
Edit block locally Download data (.npy)

Training settings

Please provide a valid training processor option
Number of training cycles should be a number
Batch size should be a number

Augmentation settings

Advanced training settings

Neural network architecture

Save
Input layer (307,200 features)
Select a backbone
Select a scoring function
SolutionsExamples / YOLOv5
Output layer (2 classes)

Model

Model version:

Last training performance (validation set)

mAP@50
0.99

Metrics (validation set)

Metric Value
mAP 0.67
mAP@[IoU=50] 0.99
mAP@[IoU=75] 0.83
mAP@[area=small] -1.00
mAP@[area=medium] 0.61
mAP@[area=large] 0.69
Recall@[max_detections=1] 0.73
Recall@[max_detections=10] 0.74
Recall@[max_detections=100] 0.74
Recall@[area=small] -1.00
Recall@[area=medium] 0.67
Recall@[area=large] 0.75
Precision score (legacy) 92.0%

Data explorer (classified samples)

Loading...

On-device performance

Inferencing time
3 ms.
Peak RAM usage
-
Flash usage
7.0M

Last training performance (validation set)

mAP@50
0.99

Metrics (validation set)

Metric Value
mAP 0.81
mAP@[IoU=50] 0.99
mAP@[IoU=75] 0.94
mAP@[area=small] -1.00
mAP@[area=medium] 0.76
mAP@[area=large] 0.82
Recall@[max_detections=1] 0.84
Recall@[max_detections=10] 0.84
Recall@[max_detections=100] 0.84
Recall@[area=small] -1.00
Recall@[area=medium] 0.80
Recall@[area=large] 0.85
Precision score (legacy) 97.0%

Data explorer (classified samples)

Loading...

On-device performance

Inferencing time
32 ms.
Flash usage
13.5M
This model won't run on MCUs. Calculated arena size is >6MB
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy