Dataset Versions
v4
2024-10-24 8:50am
Generated on Oct 24, 2024
412 Total Images
View All ImagesDataset Split
Train Set 87%
360Images
Valid Set 8%
35Images
Test Set 4%
17Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -19% and +19%
Blur: Up to 2.5px
Noise: Up to 1.01% of pixels