Dataset Versions
v1
2022-10-08 11:31am
Generated on Oct 8, 2022
246 Total Images
View All Images
Dataset Split
Train Set 88%
216Images
Valid Set 6%
14Images
Test Set 7%
16Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 40% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -61° and +61°
Saturation: Between -43% and +43%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 3px
Noise: Up to 5% of pixels
Cutout: 4 boxes with 13% size each
Mosaic: Applied