Dataset Versions

v4

2024-07-24 1-37am Adjust preprocess and augmentation

Generated on Jul 24, 2024

Dataset Split

Train Set 82%
1998Images
Valid Set 12%
285Images
Test Set 6%
143Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 2
Brightness: Between -15% and +15%
Exposure: Between -15% and +15%
Blur: Up to 1px
Noise: Up to 0.6% of pixels
Cutout: 3 boxes with 10% size each
Mosaic: Applied