Dataset Versions

v2

2024-12-08 3:18pm

Generated on Dec 8, 2024

Dataset Split

Train Set 88%
20100Images
Valid Set 8%
1800Images
Test Set 4%
900Images

Preprocessing

Tile: 10 rows x 10 columns
Modify Classes: 6 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Brightness: Between -15% and +15%

Similar Projects

See More