Dataset Versions
v5
2024-08-15 7:27pm
Generated on Aug 15, 2024
3230 Total Images
View All ImagesDataset Split
Train Set 89%
2865Images
Valid Set 8%
267Images
Test Set 3%
98Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 320x320
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -14° and +14°
Grayscale: Apply to 14% of images
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -12% and +12%
Blur: Up to 1.8px