Dataset Versions

v8

2024-11-29 10:29am

Generated on Nov 29, 2024

Dataset Split

Train Set 96%
1056Images
Valid Set 3%
29Images
Test Set 2%
19Images

Preprocessing

Auto-Orient: Applied
Static Crop: 35-66% Horizontal Region, 47-69% Vertical Region
Resize: Fit (reflect edges) in 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Saturation: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 3.94% of pixels

Similar Projects

See More
400 images 1 model
200 images 1 model