Dataset Versions
v3
2024-03-09 2:30pm
Generated on Mar 9, 2024
1641 Total Images
View All Images
Dataset Split
Train Set 91%
1497Images
Valid Set 6%
93Images
Test Set 3%
51Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 2% Minimum Zoom, 8% Maximum Zoom
Rotation: Between -10° and +10°
Hue: Between -19° and +19°
Saturation: Between -45% and +45%
Blur: Up to 1.6px
Noise: Up to 0.65% of pixels