Dataset Versions

v1

2024-09-01 6:23pm

Generated on Sep 1, 2024

Dataset Split

Train Set 87%
1032Images
Valid Set 8%
100Images
Test Set 5%
56Images

Preprocessing

Auto-Orient: Applied
Dynamic Crop: Class: Black
Resize: Stretch to 640x640
Grayscale: Applied
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal
Shear: ±10° Horizontal, ±10° Vertical
Exposure: Between -19% and +19%
Noise: Up to 0.1% of pixels

Similar Projects

See More