Dataset Versions
v2
2024-11-10 1:44pm
Generated on Nov 10, 2024
1161 Total Images
View All Images
Dataset Split
Train Set 89%
1029Images
Valid Set 10%
118Images
Test Set 1%
14Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white edges) in 1280x1280
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Grayscale: Apply to 21% of images
Hue: Between -25° and +25°
Saturation: Between -27% and +27%
Brightness: Between -24% and +24%
Exposure: Between -14% and +14%
Blur: Up to 1px
Noise: Up to 1.72% of pixels