Dataset Versions
v2
2024-09-13 8:51am
Generated on Sep 13, 2024
650 Total Images
View All Images
Dataset Split
Train Set 92%
600Images
Valid Set 4%
25Images
Test Set 4%
25Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 416x416
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Noise: Up to 0.5% of pixels