Dataset Versions

v1

2023-07-31 12:43pm

Generated on Jul 31, 2023

Dataset Split

Train Set 87%
528Images
Valid Set 7%
40Images
Test Set 6%
36Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Grayscale: Applied
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -20° and +20°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 1.75px
Noise: Up to 3% of pixels
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Rotation: Between -20° and +20°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 2.5px
Bounding Box: Noise: Up to 2% of pixels