Dataset Versions

v2

2022-11-23 11:44pm

Generated on Nov 24, 2022

Dataset Split

Train Set 87%
1236Images
Valid Set 9%
121Images
Test Set 4%
61Images

Preprocessing

Auto-Orient: Applied
Static Crop: 17-85% Horizontal Region, 45-83% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Blur: Up to 10px

Similar Projects

See More
554 images 2 models
232 images 1 model