Dataset Versions

v2

2024-08-30 4:44pm

Generated on Aug 30, 2024

Dataset Split

Train Set 95%
2172Images
Valid Set 3%
72Images
Test Set 2%
35Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Exposure: Between -10% and +10%