Dataset Versions
Versions
v1
2023-07-05 10:57pm
Generated on Jul 5, 2023
314 Total Images
View All ImagesDataset Split
Train Set 92%
288Images
Valid Set 8%
26Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Static Crop: 15-58% Horizontal Region, 25-66% Vertical Region
Resize: Fill (with center crop) in 640x640
Modify Classes: 2 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Shear: ±45° Horizontal, ±45° Vertical
Saturation: Between -58% and +58%
Brightness: Between -53% and +53%
Exposure: Between -45% and +45%
Blur: Up to 9.75px
Noise: Up to 19% of pixels