Dataset Versions
Versions
v1
2024-02-09 12:35am
Generated on Feb 8, 2024
162 Total Images
View All Images
Dataset Split
Train Set 80%
129Images
Valid Set 12%
19Images
Test Set 9%
14Images
Preprocessing
Auto-Orient: Applied
Static Crop: 20-73% Horizontal Region, 4-71% Vertical Region
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°
Shear: ±13° Horizontal, ±3° Vertical
Brightness: Between -23% and +23%
Blur: Up to 2.4px
Noise: Up to 1.8% of pixels