Dataset Versions
Versions
v1
2024-11-04 1:02pm
Generated on Nov 4, 2024
253 Total Images
View All Images
Dataset Split
Train Set 88%
222Images
Valid Set 8%
21Images
Test Set 4%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 2% Minimum Zoom, 39% Maximum Zoom
Shear: ±13° Horizontal, ±21° Vertical
Hue: Between -24° and +24°
Saturation: Between -36% and +36%
Brightness: Between -20% and +20%
Noise: Up to 0.1% of pixels