Dataset Versions
v7
2024-11-07 3:34am
Generated on Nov 7, 2024
1267 Total Images
View All ImagesDataset Split
Train Set 98%
1242Images
Valid Set 2%
22Images
Test Set 0%
3Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Saturation: Between -13% and +13%
Exposure: Between -15% and +15%
Blur: Up to 1.2px
Noise: Up to 5.13% of pixels
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical