Dataset Versions

v5

2022-10-16 11:55am

Generated on Oct 16, 2022

Dataset Split

Train Set 92%
1944Images
Valid Set 4%
79Images
Test Set 4%
85Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 64% Maximum Zoom
Rotation: Between -35° and +35°
Hue: Between -60° and +60°
Saturation: Between -60% and +60%