Dataset Versions
Versions
v1
2023-09-09 1:46am
Generated on Sep 8, 2023
242 Total Images
View All Images
Dataset Split
Train Set 92%
222Images
Valid Set 5%
13Images
Test Set 3%
7Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -29° and +29°
Grayscale: Apply to 100% of images
Hue: Between -180° and +180°
Saturation: Between -99% and +99%
Exposure: Between -25% and +25%
Blur: Up to 3.75px
Noise: Up to 7% of pixels
Cutout: 16 boxes with 12% size each