Dataset Versions

v2

2024-12-05 12:46am

Generated on Dec 4, 2024

Dataset Split

Train Set 88%
219Images
Valid Set 8%
20Images
Test Set 4%
10Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 550x550
Grayscale: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Grayscale: Apply to 23% of images
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%