Dataset Versions
v2
preprocessed_augmented
Generated on Jul 18, 2023
87 Total Images
View All ImagesDataset Split
Train Set 86%
75Images
Valid Set 9%
8Images
Test Set 5%
4Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Modify Classes: 0 remapped, 1 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
Rotation: Between -9° and +9°
Brightness: Between -10% and +10%
Noise: Up to 5% of pixels