Dataset Versions
Versions
v1
2024-01-09 1:20am
Generated on Jan 8, 2024
480 Total Images
View All Images
Dataset Split
Train Set 94%
450Images
Valid Set 6%
30Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Static Crop: 12-95% Horizontal Region, 9-100% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 17% Maximum Zoom
Grayscale: Apply to 8% of images
Hue: Between -17° and +17°
Saturation: Between -25% and +25%
Cutout: 5 boxes with 36% size each