cars-in-parking-garage - Object detection

ei-ready-device-testing / cars-in-parking-garage Public

Target: Qualcomm Dragonwing RB3 Gen 2 Development Kit Clone this project

Object detection settings

Training settings

Training processor

Please provide a valid training processor option

Number of training cycles

Number of training cycles should be a number

Learning rate

Learning rate should be a number

Model size

Use pretrained weights

Advanced training settings

Validation set size

Please provide a valid number for the train/validate split (between 0 and 1)

Split train/validation set on metadata key

Profile int8 model

Batch size

Batch size should be a number

Freeze backbone

Architecture type

Spatial Augmentation

Color space Augmentation

Early stopping start epoch

Early stopping start epoch should be a number

Neural network architecture

Save

Input layer (1,228,800 features)

YOLO-Pro

Developer preview

Output layer (1 classes)

Model

Model version:

Metric	Value
mAP	0.69
mAP@[IoU=50]	1.00
mAP@[IoU=75]	0.77
mAP@[area=small]	-1.00
mAP@[area=medium]	0.64
mAP@[area=large]	0.70
Recall@[max_detections=1]	0.32
Recall@[max_detections=10]	0.73
Recall@[max_detections=100]	0.73
Recall@[area=small]	-1.00
Recall@[area=medium]	0.66
Recall@[area=large]	0.74

Last training performance (validation set)

Precision score

97.4%

Metrics (validation set)

Metric	Value
mAP	0.74
mAP@[IoU=50]	1.00
mAP@[IoU=75]	0.82
mAP@[area=small]	-1.00
mAP@[area=medium]	0.73
mAP@[area=large]	0.75
Recall@[max_detections=1]	0.34
Recall@[max_detections=10]	0.79
Recall@[max_detections=100]	0.79
Recall@[area=small]	-1.00
Recall@[area=medium]	0.75
Recall@[area=large]	0.80

On-device performance

Inferencing time

83 ms.

Peak RAM usage

Flash usage

27.6M

This model won't run on MCUs. Calculated arena size is >6MB

These users will be notified over email when this job finishes.

	Name
	Joshua Buck Edge Impulse staff

Object detection settings

Training settings

Augmentation settings

Advanced training settings

Neural network architecture

Model

Last training performance (validation set)

Precision score

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (full training set)

On-device performance

Inferencing time

Peak RAM usage

Flash usage

Last training performance (validation set)

Precision score

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (full training set)

On-device performance

Inferencing time

Peak RAM usage

Flash usage

Object detection settings

Training settings

Augmentation settings

Advanced training settings

Neural network architecture

Model

Last training performance (validation set)

Precision score

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (full training set)

Settings

On-device performance

Inferencing time

Peak RAM usage

Flash usage

Last training performance (validation set)

Precision score

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (full training set)

Settings

On-device performance

Inferencing time

Peak RAM usage

Flash usage