Dataset Versions
v10
2023-08-31 4:11pm
Generated on Aug 31, 2023
5540 Total Images
View All Images
Dataset Split
Train Set 88%
4860Images
Valid Set 8%
455Images
Test Set 4%
225Images
Preprocessing
Auto-Orient: Applied
Modify Classes: 2 remapped, 1 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 13% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -16° and +16°
Saturation: Between -14% and +14%
Brightness: Between -14% and +14%
Exposure: Between -2% and +2%
Blur: Up to 0.75px
Noise: Up to 1% of pixels