Dataset Versions
v3
2022-12-28 11:12pm
Generated on Dec 28, 2022
662 Total Images
View All Images
Dataset Split
Train Set 85%
561Images
Valid Set 8%
50Images
Test Set 8%
51Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -35° and +35°
Grayscale: Apply to 25% of images
Hue: Between -100° and +100°
Brightness: Between -25% and +25%
Blur: Up to 10px
Noise: Up to 5% of pixels