Dataset Versions

v1

2023-08-20 4:38pm

Generated on Aug 20, 2023

Dataset Split

Train Set 87%
8355Images
Valid Set 8%
797Images
Test Set 4%
397Images

Preprocessing

Auto-Orient: Applied
Static Crop: 21-100% Horizontal Region, 27-70% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Modify Classes: 8 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Grayscale: Apply to 100% of images
Blur: Up to 1.75px
Noise: Up to 15% of pixels