Edge Impulse Experts / orange-avocado-stm32n6-object-detection Public
Target: ST STM32N6 (Cortex-M55 800MHz + ST Neural-ART accelerator) Clone this project

Object detection settings

Switch to Keras (expert) mode Switch to visual (simple) mode Edit block locally

Training settings

Please provide a valid training processor option
Number of training cycles should be a number
Learning rate should be a number

Augmentation settings

Advanced training settings

Neural network architecture

Save
Input layer (110,592 features)
Select a backbone
Select a scoring function
YOLO-Pro
Output layer (2 classes)

Model

Model version:

Last training performance (validation set)

mAP@50
1.00

Metrics (validation set)

Metric Value
mAP 0.81
mAP@[IoU=50] 1.00
mAP@[IoU=75] 1.00
mAP@[area=small] -1.00
mAP@[area=medium] 0.81
mAP@[area=large] -1.00
Recall@[max_detections=1] 0.83
Recall@[max_detections=10] 0.83
Recall@[max_detections=100] 0.83
Recall@[area=small] -1.00
Recall@[area=medium] 0.83
Recall@[area=large] -1.00
Precision score (legacy) 98.8%

Data explorer (classified samples)

Loading...

On-device performance

Engine:
EON™ Compiler TensorFlow Lite
Inferencing time
131 ms.
Peak RAM usage
302.5K
Flash usage
844.0K

Last training performance (validation set)

mAP@50
1.00

Metrics (validation set)

Metric Value
mAP 0.84
mAP@[IoU=50] 1.00
mAP@[IoU=75] 1.00
mAP@[area=small] -1.00
mAP@[area=medium] 0.84
mAP@[area=large] -1.00
Recall@[max_detections=1] 0.87
Recall@[max_detections=10] 0.87
Recall@[max_detections=100] 0.87
Recall@[area=small] -1.00
Recall@[area=medium] 0.87
Recall@[area=large] -1.00
Precision score (legacy) 99.0%

Data explorer (classified samples)

Loading...

On-device performance

Engine:
EON™ Compiler TensorFlow Lite
Inferencing time
N/A
Peak RAM usage
903.7K
Flash usage
2.3M
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy