Dataset Versions

v1

LIthology Classifier

Generated on Jul 10, 2024

Dataset Split

Train Set 81%
19921Images
Valid Set 10%
2338Images
Test Set 9%
2257Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 500x250
Tile: 4 rows x 4 columns
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down