Dataset Versions
v3
2024-09-17 12:04pm
Generated on Sep 17, 2024
1512 Total Images
View All Images
Dataset Split
Train Set 88%
1323Images
Valid Set 8%
126Images
Test Set 4%
63Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 512x512
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 17% of images
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Noise: Up to 0.85% of pixels