Dataset Versions
v6
final1
Generated on May 1, 2024
2582 Total Images
View All Images
Dataset Split
Train Set 90%
2328Images
Valid Set 4%
102Images
Test Set 6%
152Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Saturation: Between -34% and +34%
Brightness: Between -15% and +15%
Exposure: Between -17% and +17%
Blur: Up to 2px
Bounding Box: Shear: ±11° Horizontal, ±11° Vertical