Dataset Versions
v4
2024-01-30 2:10pm
Generated on Jan 30, 2024
523 Total Images
View All Images
Dataset Split
Train Set 92%
483Images
Valid Set 4%
20Images
Test Set 4%
20Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 39% Maximum Zoom
Grayscale: Apply to 41% of images
Hue: Between -51° and +51°
Saturation: Between -50% and +50%
Brightness: Between -46% and +46%
Exposure: Between -20% and +20%
Blur: Up to 2.7px
Noise: Up to 3.95% of pixels
Cutout: 4 boxes with 5% size each
Bounding Box: Brightness: Between -25% and +25%