Dataset Versions
v3
2022-07-25 10:49am
Generated on Jul 25, 2022
217 Total Images
View All Images
Dataset Split
Train Set 95%
207Images
Valid Set 2%
4Images
Test Set 3%
6Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 52% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -7° and +7°
Saturation: Between -4% and +4%
Brightness: Between -7% and +7%
Exposure: Between -6% and +6%
Blur: Up to 1.75px
Noise: Up to 5% of pixels
Cutout: 25 boxes with 9% size each