Dataset Versions
Versions
v1
2023-11-10 6:33pm
Generated on Nov 10, 2023
62 Total Images
View All Images
Dataset Split
Train Set 87%
54Images
Valid Set 8%
5Images
Test Set 5%
3Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 18% Maximum Zoom
Rotation: Between -27° and +27°
Shear: ±15° Horizontal, ±9° Vertical
Grayscale: Apply to 57% of images
Hue: Between -69° and +69°
Saturation: Between -47% and +47%
Brightness: Between -15% and +15%
Exposure: Between -17% and +17%
Blur: Up to 0.75px
Noise: Up to 3% of pixels
Cutout: 3 boxes with 4% size each