Dataset Versions
Versions
v1
2023-08-20 8:50pm
Generated on Aug 21, 2023
573 Total Images
View All ImagesDataset Split
Train Set 87%
501Images
Valid Set 8%
45Images
Test Set 5%
27Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Mosaic: Applied