Dataset Versions

v1

2023-10-09 10:56am

Generated on Oct 9, 2023

Dataset Split

Train Set 85%
423Images
Valid Set 9%
44Images
Test Set 6%
32Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Saturation: Between -49% and +49%
Brightness: Between -41% and +41%
Exposure: Between -7% and +7%
Blur: Up to 1.5px
Noise: Up to 7% of pixels