Dataset Versions

v6

2024-04-02 11:52am

Generated on Apr 2, 2024

Dataset Split

Train Set 83%
252Images
Valid Set 5%
16Images
Test Set 11%
34Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
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