Dataset Versions
v5
2023-12-26 6:52pm
Generated on Dec 26, 2023
545 Total Images
View All ImagesDataset Split
Train Set 90%
492Images
Valid Set 6%
35Images
Test Set 3%
18Images
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 -15° and +15°
Grayscale: Apply to 1% of images
Brightness: Between -25% and +25%
Blur: Up to 0.25px
Noise: Up to 3% of pixels