Versions
v4
2025-01-08 4:14pm
Generated on Jan 8, 2025
734 Total Images
View All Images
Dataset Split
Train Set 87%
642Images
Valid Set 8%
61Images
Test Set 4%
31Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -20% and +20%
Blur: Up to 2.5px
Noise: Up to 0.73% of pixels