Dataset Versions

v2

2023-11-08 10:46pm

Generated on Nov 8, 2023

Dataset Split

Train Set 86%
1755Images
Valid Set 9%
184Images
Test Set 5%
101Images

Preprocessing

Auto-Orient: Applied
Isolate Objects: Applied
Static Crop: 6-86% Horizontal Region, 13-97% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±26° Vertical
Hue: Between -38° and +38°
Blur: Up to 2px
Cutout: 25 boxes with 19% size each
Mosaic: Applied
Bounding Box: Rotation: Between -33° and +33°
Bounding Box: Blur: Up to 6.25px
Bounding Box: Noise: Up to 5% of pixels

Similar Projects

See More
185 images 1 model