Dataset Versions

v2

2024-11-08 4:02am

Generated on Nov 8, 2024

Dataset Split

Train Set 87%
1971Images
Valid Set 8%
190Images
Test Set 5%
107Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±28° Vertical
Grayscale: Apply to 15% of images
Hue: Between -53° and +53°
Saturation: Between -53% and +53%
Blur: Up to 7.9px
Noise: Up to 6.47% of pixels
Mosaic: Applied
Bounding Box: Brightness: Between -42% and +42%

Similar Projects

See More
223 images 1 model