Dataset Versions
v2
2024-09-28 11:30am
Generated on Sep 28, 2024
1182 Total Images
View All Images
Dataset Split
Train Set 88%
1035Images
Valid Set 8%
97Images
Test Set 4%
50Images
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 -30° and +30°
Grayscale: Apply to 30% of images
Hue: Between -30° and +30°
Saturation: Between -30% and +30%
Brightness: Between -30% and +30%
Exposure: Between -30% and +30%
Blur: Up to 5px
Noise: Up to 1.88% of pixels