Dataset Versions

v3

2022-08-24 1:09pm

Generated on Aug 24, 2022

Dataset Split

Train Set 87%
111Images
Valid Set 10%
13Images
Test Set 2%
3Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±15° Horizontal, ±15° Vertical