Dataset Versions

v4

2023-03-23 5:14pm

Generated on Mar 23, 2023

Dataset Split

Train Set 85%
1590Images
Valid Set 10%
185Images
Test Set 5%
90Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 4 remapped, 0 dropped
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -10° and +10°
Saturation: Between -25% and +25%
Exposure: Between -25% and +25%