Dataset Versions

v4

finaltraining

Generated on Mar 15, 2023

Dataset Split

Train Set 87%
353Images
Valid Set 8%
34Images
Test Set 5%
19Images

Preprocessing

Auto-Adjust Contrast: Using Histogram Equalization
Filter Null: Require at least 98% of images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal
Grayscale: Apply to 25% of images
Exposure: Between -10% and +10%