Dataset Versions
Versions
v1
2023-12-19 4:38pm
Generated on Dec 19, 2023
416 Total Images
View All Images
Dataset Split
Train Set 92%
384Images
Valid Set 4%
16Images
Test Set 4%
16Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -45° and +45°
Grayscale: Apply to 10% of images
Hue: Between -30° and +30°
Saturation: Between -56% and +56%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels