Dataset Versions
v2
2023-09-18 1:37pm
Generated on Sep 18, 2023
1268 Total Images
View All Images
Dataset Split
Train Set 88%
1110Images
Valid Set 7%
84Images
Test Set 6%
74Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 32-88% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Augmentations
Outputs per training example: 3
Shear: ±45° Horizontal, ±40° Vertical
Grayscale: Apply to 100% of images
Hue: Between -62° and +62°
Saturation: Between -70% and +70%
Brightness: Between -57% and +57%
Exposure: Between -56% and +56%
Blur: Up to 4px
Noise: Up to 10% of pixels
Cutout: 25 boxes with 3% size each