Dataset Versions

v2

2023-12-27 12:57pm

Generated on Dec 27, 2023

Dataset Split

Train Set 88%
885Images
Valid Set 8%
83Images
Test Set 4%
42Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Exposure: Between -25% and +25%
Cutout: 3 boxes with 10% size each