Edge Impulse Experts / edge-impulse-object-detection-with-vlm 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 number of training cycles (numeric only)
Please provide a valid number for the learning rate (between 0 and 1)
Please provide a valid training processor option

Augmentation settings

Advanced training settings

Neural network architecture

Save
Input layer (1,228,800 features)
Edge Impulse Experts / YOLOv5(added by Solomon Githu)
Output layer (6 classes)

Model

Model version:

Last training performance (validation set)

Precision score
43.0%

Metrics (validation set)

Metric Value
mAP 0.23
mAP@[IoU=50] 0.41
mAP@[IoU=75] 0.20
mAP@[area=small] 0.02
mAP@[area=medium] 0.04
mAP@[area=large] 0.26
Recall@[max_detections=1] 0.30
Recall@[max_detections=10] 0.36
Recall@[max_detections=100] 0.37
Recall@[area=small] 0.07
Recall@[area=medium] 0.08
Recall@[area=large] 0.42

Data explorer (full training set)

Loading...

On-device performance

Engine:
EON™ Compiler TensorFlow Lite
Inferencing time
N/A
Flash usage
3.5M
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