Dataset Versions
v2
2024-07-23 2:24pm
Generated on Jul 23, 2024
240 Total Images
View All Images
Dataset Split
Train Set 90%
216Images
Valid Set 5%
13Images
Test Set 5%
11Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 26% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±14° Horizontal, ±14° Vertical
Grayscale: Apply to 15% of images
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Brightness: Between -23% and +23%
Exposure: Between -10% and +10%
Blur: Up to 0.6px
Noise: Up to 1.09% of pixels
Cutout: 8 boxes with 7% size each
Bounding Box: Flip: Horizontal
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Shear: ±10° Horizontal, ±10° Vertical
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 0.6px
Bounding Box: Noise: Up to 0.1% of pixels