Dataset Versions

v1

2023-07-11 8:03pm

Generated on Jul 11, 2023

Dataset Split

Train Set 87%
75Images
Valid Set 8%
7Images
Test Set 5%
4Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 2% Maximum Zoom
Shear: ±33° Horizontal, ±26° Vertical
Grayscale: Apply to 32% of images
Noise: Up to 14% of pixels
Mosaic: Applied
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down