Dataset Versions
v3
2024-10-01 2:02am
Generated on Oct 1, 2024
669 Total Images
View All ImagesDataset Split
Train Set 92%
618Images
Valid Set 8%
51Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -20° and +20°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -35% and +35%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 1.8px
Noise: Up to 0.46% of pixels