Dataset Versions
Versions
v1
2024-12-09 6:55pm
Generated on Dec 10, 2024
319 Total Images
View All Images
Dataset Split
Train Set 87%
279Images
Valid Set 8%
27Images
Test Set 4%
13Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 640x640
Grayscale: Applied
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 0% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±5° Horizontal, ±4° Vertical
Grayscale: Apply to 19% of images
Hue: Between -10° and +10°
Saturation: Between -25% and +25%
Brightness: Between -15% and +0%
Exposure: Between -9% and +9%
Blur: Up to 2.5px
Noise: Up to 0.02% of pixels