Dataset Versions
v11
12-03-24 V3 V2
Generated on Dec 3, 2024
620 Total Images
View All Images
Dataset Split
Train Set 90%
560Images
Valid Set 6%
40Images
Test Set 3%
20Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 4
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images