Dataset Versions

v1

2024-10-21 2:31pm

Generated on Oct 21, 2024

Dataset Split

Train Set 88%
2688Images
Valid Set 8%
256Images
Test Set 4%
128Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Hue: Between -108° and +108°
Saturation: Between -34% and +34%
Brightness: Between -62% and +62%
Cutout: 5 boxes with 4% size each