RealNOGADA Dataset
v5
2024-07-10 8:00pm
Generated on Jul 10, 2024
13060 Total Images
View All Images
Dataset Split
Train Set 90%
11790Images
Valid Set 8%
1019Images
Test Set 2%
251Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x480
Augmentations
Outputs per training example: 3
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Blur: Up to 3px
Cutout: 2 boxes with 15% size each