Dataset Versions
v1
2024-09-04 5:43pm
Generated on Sep 4, 2024
1389 Total Images
View All Images
Dataset Split
Train Set 92%
1281Images
Valid Set 6%
80Images
Test Set 2%
28Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 320x320
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 8% Maximum Zoom
Rotation: Between -28° and +28°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -21° and +21°
Saturation: Between -25% and +25%
Brightness: Between -21% and +21%
Exposure: Between -13% and +13%
Blur: Up to 2.5px
Noise: Up to 1.05% of pixels
Cutout: 4 boxes with 10% size each