Dataset Versions

v3

2023-05-21 10:35am

Generated on May 21, 2023

Dataset Split

Train Set 87%
1278Images
Valid Set 9%
130Images
Test Set 4%
60Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Modify Classes: 10 remapped, 1 dropped
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal
Brightness: Between -25% and +25%
Noise: Up to 5% of pixels
Mosaic: Applied