Dataset Versions

v9

2024-04-09 1:13pm

Generated on Apr 9, 2024

Dataset Split

Train Set 56%
120Images
Valid Set 7%
15Images
Test Set 37%
79Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Saturation: Between -20% and +20%
Brightness: Between -17% and +17%
Exposure: Between -8% and +8%

Similar Projects

See More