Dataset Versions

v5

2024-08-25 8:38am

Generated on Aug 25, 2024

Dataset Split

Train Set 97%
132Images
Valid Set 2%
3Images
Test Set 1%
1Images

Preprocessing

Resize: Fill (with center crop) in 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±13° Horizontal, ±12° Vertical
Grayscale: Apply to 15% of images
Blur: Up to 0.6px
Noise: Up to 1.85% of pixels