Dataset Versions
v8
2023-09-21 12:17pm
Generated on Sep 21, 2023
6490 Total Images
View All Images
Dataset Split
Train Set 89%
5745Images
Valid Set 10%
665Images
Test Set 1%
80Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white edges) in 640x640
Modify Classes: 0 remapped, 1 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -45° and +45°
Hue: Between -15° and +15°
Saturation: Between -29% and +29%
Blur: Up to 0.75px
Noise: Up to 5% of pixels
Cutout: 6 boxes with 10% size each