Dataset Versions
v2
nul
Generated on Oct 13, 2024
564 Total Images
View All Images
Dataset Split
Train Set 88%
495Images
Valid Set 8%
45Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x300
Augmentations
Outputs per training example: 3
Rotation: Between -26° and +26°
Grayscale: Apply to 12% of images
Hue: Between -21° and +21°
Saturation: Between -62% and +62%
Exposure: Between -13% and +13%
Blur: Up to 1.2px