Dataset Versions
v3
2023-06-22 12:09pm
Generated on Jun 22, 2023
336 Total Images
View All Images
Dataset Split
Train Set 88%
294Images
Valid Set 8%
28Images
Test Set 4%
14Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white edges) in 640x640
Modify Classes: 0 remapped, 2 dropped
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Grayscale: Apply to 10% of images
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical