Dataset Versions
v2
2024-09-27 10:31am
Generated on Sep 27, 2024
244 Total Images
View All ImagesDataset Split
Train Set 89%
216Images
Valid Set 8%
20Images
Test Set 3%
8Images
Preprocessing
Auto-Orient: Applied
Static Crop: 29-65% Horizontal Region, 38-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 14% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±0° Vertical
Grayscale: Apply to 100% of images
Hue: Between -24° and +24°
Saturation: Between -31% and +31%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Noise: Up to 0.97% of pixels