Dataset Versions

v1

2023-04-22 4:56pm

Generated on Apr 22, 2023

Dataset Split

Train Set 87%
2373Images
Valid Set 10%
276Images
Test Set 3%
69Images

Preprocessing

Auto-Orient: Applied
Static Crop: 32-75% Horizontal Region, 25-81% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Cutout: 3 boxes with 10% size each

Similar Projects

See More