Dataset Versions
v5
sharath
Generated on Feb 27, 2023
1524 Total Images
View All Images
Dataset Split
Train Set 88%
1344Images
Valid Set 8%
120Images
Test Set 4%
60Images
Preprocessing
Auto-Orient: Applied
Grayscale: Applied
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -5% and +5%
Blur: Up to 0.5px