Dataset Versions

v1

2023-09-19 8:06am

Generated on Sep 19, 2023

Dataset Split

Train Set 88%
3762Images
Valid Set 8%
357Images
Test Set 4%
179Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 3 dropped

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 2.5px
Noise: Up to 5% of pixels