Dataset Versions
Versions
v1
2024-06-24 3:03pm
Generated on Jun 24, 2024
13609 Total Images
View All Images
Dataset Split
Train Set 94%
12828Images
Valid Set 3%
419Images
Test Set 3%
362Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -14° and +14°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -34% and +34%
Brightness: Between -15% and +15%
Blur: Up to 3.6px
Noise: Up to 2% of pixels
Cutout: 4 boxes with 15% size each