Dataset Versions

v4

2024-05-17 11:01am

Generated on May 17, 2024

Dataset Split

Train Set 86%
2223Images
Valid Set 12%
299Images
Test Set 3%
75Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Grayscale: Apply to 15% of images
Blur: Up to 2px
Noise: Up to 1.05% of pixels
Cutout: 3 boxes with 10% size each