Dataset Versions
Versions
v1
2023-11-11 10:38am
Generated on Nov 11, 2023
1059 Total Images
View All Images
Dataset Split
Train Set 88%
927Images
Valid Set 8%
88Images
Test Set 4%
44Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 28% Maximum Zoom
Rotation: Between -21° and +21°
Shear: ±21° Horizontal, ±20° Vertical
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Saturation: Between -39% and +39%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 7% of pixels