Dataset Versions
v1
2024-04-18 7:00pm
Generated on Apr 18, 2024
579 Total Images
View All Images
Dataset Split
Train Set 88%
507Images
Valid Set 8%
48Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x480
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 9% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Saturation: Between -60% and +60%
Brightness: Between -23% and +23%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.53% of pixels
Cutout: 9 boxes with 14% size each
Mosaic: Applied
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom