Dataset Versions
Versions
v1
2023-02-17 4:02pm
Generated on Feb 17, 2023
217 Total Images
View All Images
Dataset Split
Train Set 87%
189Images
Valid Set 8%
18Images
Test Set 5%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Shear: ±18° Horizontal, ±16° Vertical
Exposure: Between -29% and +29%
Blur: Up to 3px
Noise: Up to 9% of pixels
Cutout: 8 boxes with 13% size each