Dataset Versions

v6

avlin_azmon

Generated on Sep 29, 2024

Dataset Split

Train Set 91%
3924Images
Valid Set 9%
400Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Static Crop: 3-100% Horizontal Region, 3-100% Vertical Region
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 5% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±3° Horizontal, ±3° Vertical
Grayscale: Apply to 5% of images
Hue: Between -14° and +14°
Saturation: Between -18% and +18%
Brightness: Between -10% and +10%
Exposure: Between -5% and +5%
Blur: Up to 0.1px
Noise: Up to 0.05% of pixels

Similar Projects

See More