Dataset Versions

v1

2024-07-26 3:55pm

Generated on Jul 26, 2024

Dataset Split

Train Set 88%
372Images
Valid Set 8%
36Images
Test Set 4%
16Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Grayscale: Applied
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Blur: Up to 2px
Noise: Up to 0.73% of pixels