Dataset Versions
v1
2024-10-14 12:58pm
Generated on Oct 14, 2024
1141 Total Images
View All Images
Dataset Split
Train Set 88%
999Images
Valid Set 8%
95Images
Test Set 4%
47Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white edges) in 640x640
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