Dataset Versions
v3
2024-01-30 9:19am
Generated on Jan 30, 2024
930 Total Images
View All Images
Dataset Split
Train Set 90%
837Images
Valid Set 5%
46Images
Test Set 5%
47Images
Preprocessing
Auto-Orient: Applied
Static Crop: 24-75% Horizontal Region, 30-66% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -25° and +25°
Exposure: Between -14% and +14%
Noise: Up to 1.37% of pixels