Dataset Versions
v1
2024-12-11 11:16am
Generated on Dec 11, 2024
233 Total Images
View All Images
Dataset Split
Train Set 88%
204Images
Valid Set 8%
19Images
Test Set 4%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 20% of images
Hue: Between -24° and +24°
Exposure: Between -15% and +15%
Blur: Up to 1.9px
Noise: Up to 1.99% of pixels
Cutout: 6 boxes with 10% size each