Dataset Versions

v10

Resize 640x640

Generated on Aug 14, 2024

Dataset Split

Train Set 88%
1992Images
Valid Set 8%
190Images
Test Set 4%
94Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require at least 60% of images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -13° and +13°
Brightness: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.25% of pixels