Dataset Versions

v2

2024-09-25 11:49am

Generated on Sep 25, 2024

Dataset Split

Train Set 90%
54Images
Valid Set 7%
4Images
Test Set 3%
2Images

Preprocessing

Auto-Orient: Applied
Dynamic Crop: Class: PL_SLAB4
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Bounding Box: Exposure: Between -10% and +10%