Dataset Versions
v9
2024-10-22 9:44am
Generated on Oct 22, 2024
8485 Total Images
View All Images
Dataset Split
Train Set 93%
7915Images
Valid Set 4%
356Images
Test Set 3%
214Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 360x360
Grayscale: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%