Dataset Versions
Versions
v1
2023-08-26 12:39pm
Generated on Aug 26, 2023
4013 Total Images
View All Images
Dataset Split
Train Set 88%
3513Images
Valid Set 8%
334Images
Test Set 4%
166Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 224x224
Augmentations
Outputs per training example: 3
Flip: Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -44° and +44°
Shear: ±18° Horizontal, ±9° Vertical
Hue: Between -83° and +83°
Saturation: Between -55% and +55%
Brightness: Between -45% and +45%
Exposure: Between -10% and +10%
Blur: Up to 1px
Noise: Up to 3% of pixels
Cutout: 5 boxes with 5% size each