Dataset Versions

v8

2024-12-04 6:39pm

Generated on Dec 4, 2024

Dataset Split

Train Set 95%
3165Images
Valid Set 3%
89Images
Test Set 2%
83Images

Preprocessing

Auto-Orient: Applied
Static Crop: 16-78% Horizontal Region, 6-86% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Modify Classes: 2 remapped, 3 dropped

Augmentations

Outputs per training example: 5
Flip: Horizontal
Grayscale: Apply to 10% of images
Hue: Between -8° and +8°
Saturation: Between -22% and +22%
Exposure: Between -10% and +10%
Noise: Up to 1.46% of pixels

Similar Projects

See More