Dataset Versions

v17

2023-12-04 10:42pm

Generated on Dec 4, 2023

Dataset Split

Train Set 97%
4720Images
Valid Set 3%
132Images
Test Set 1%
30Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Shear: ±0° Horizontal, ±45° Vertical
Exposure: Between -24% and +24%
Blur: Up to 2.5px
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Blur: Up to 2.5px