Dataset Versions

v7

2024-03-24 10:59pm

Generated on Mar 24, 2024

Dataset Split

Train Set 94%
25102Images
Valid Set 4%
1025Images
Test Set 2%
512Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require at least 98% of images to contain annotations.

Augmentations

Outputs per training example: 7
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%