Dataset Versions
v3
2024-06-29 5:44pm
Generated on Jun 29, 2024
1241 Total Images
View All Images
Dataset Split
Train Set 88%
1086Images
Valid Set 8%
103Images
Test Set 4%
52Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 28% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%