Dataset Versions

v4

2024-09-23 9:48am

Generated on Sep 23, 2024

Dataset Split

Train Set 88%
270Images
Valid Set 8%
25Images
Test Set 4%
12Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Modify Classes: 0 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Saturation: Between -25% and +25%
Blur: Up to 1px
Noise: Up to 1.8% of pixels
Bounding Box: Exposure: Between -15% and +15%
Bounding Box: Noise: Up to 10% of pixels