Dataset Versions

v1

2024-10-10 6:21am

Generated on Oct 10, 2024

Dataset Split

Train Set 90%
1350Images
Valid Set 6%
90Images
Test Set 4%
60Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Tile: 1 rows x 1 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±13° Vertical
Noise: Up to 0.54% of pixels