Dataset Versions

v2

Test1

Generated on Aug 24, 2024

Dataset Split

Train Set 87%
294Images
Valid Set 9%
30Images
Test Set 4%
13Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -11° and +11°
Brightness: Between -23% and +23%
Exposure: Between -10% and +10%
Noise: Up to 1.72% of pixels