Dataset Versions
v2
2024-08-29 11:43am
Generated on Aug 29, 2024
432 Total Images
View All Images
Dataset Split
Train Set 88%
378Images
Valid Set 8%
36Images
Test Set 4%
18Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 96x96
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 9% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -20% and +20%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels
Cutout: 4 boxes with 8% size each