Dataset Versions
v5
V5_dataset
Generated on Jan 29, 2024
543 Total Images
View All Images
Dataset Split
Train Set 87%
471Images
Valid Set 9%
48Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 128x128
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -20° and +20°
Blur: Up to 2.5px
Noise: Up to 0.85% of pixels
Cutout: 4 boxes with 15% size each