Dataset Versions

v2

2024-08-28 5:23pm

Generated on Aug 28, 2024

Dataset Split

Train Set 93%
216Images
Valid Set 5%
11Images
Test Set 3%
6Images

Preprocessing

Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -25° and +25°
Shear: ±32° Horizontal, ±14° Vertical
Blur: Up to 1.3px
Cutout: 6 boxes with 14% size each