Dataset Versions

v2

2022-08-24 1:03pm

Generated on Aug 24, 2022

Dataset Split

Train Set 89%
1272Images
Valid Set 9%
131Images
Test Set 2%
24Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 4 rows x 4 columns
Filter Null: Require all images to contain annotations.

Augmentations

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