Dataset Versions

v1

6cls_classification

Generated on Jun 13, 2022

Dataset Split

Train Set 88%
27360Images
Valid Set 8%
2604Images
Test Set 4%
1304Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%