Dataset Versions
v2
2024-12-24 6:56am
Generated on Dec 24, 2024
5130 Total Images
View All Images
Dataset Split
Train Set 87%
4488Images
Valid Set 8%
429Images
Test Set 4%
213Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 224x224
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -10° and +10°
Shear: ±5° Horizontal, ±5° Vertical
Saturation: Between -30% and +30%
Brightness: Between -30% and +30%
Exposure: Between -15% and +15%
Cutout: 1 boxes with 5% size each
