Dataset Versions

v1

2022-12-31 3:44pm

Generated on Dec 31, 2022

Dataset Split

Train Set 83%
3210Images
Valid Set 1%
55Images
Test Set 15%
580Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 10px
Cutout: 10 boxes with 10% size each