Dataset Versions
v2
2024-09-20 5:19am
Generated on Sep 20, 2024
1125 Total Images
View All Images
Dataset Split
Train Set 92%
1032Images
Valid Set 4%
50Images
Test Set 4%
43Images
Preprocessing
Auto-Orient: Applied
Static Crop: 17-83% Horizontal Region, 2-99% Vertical Region
Resize: Stretch to 1024x1024
Auto-Adjust Contrast: Using Contrast Stretching
Filter Null: Require at least 10% of images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Saturation: Between -15% and +15%
Brightness: Between 0% and +20%
Exposure: Between -3% and +3%