Dataset Versions
Versions
v1
2023-11-16 11:47am
Generated on Nov 16, 2023
658 Total Images
View All Images
Dataset Split
Train Set 88%
576Images
Valid Set 8%
55Images
Test Set 4%
27Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -23° and +23°
Shear: ±16° Horizontal, ±26° Vertical
Grayscale: Apply to 47% of images
Hue: Between -80° and +80°
Saturation: Between -62% and +62%
Brightness: Between -38% and +38%
Exposure: Between -41% and +41%
Blur: Up to 5.25px
Noise: Up to 8% of pixels
Cutout: 4 boxes with 8% size each