Dataset Versions

v4

2023-08-01 10:36am

Generated on Aug 1, 2023

Dataset Split

Train Set 88%
3195Images
Valid Set 8%
303Images
Test Set 4%
152Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x480

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels