Dataset Versions
Versions
v1
2022-11-15 1:04pm
Generated on Nov 15, 2022
715 Total Images
View All Images
Dataset Split
Train Set 92%
660Images
Valid Set 8%
55Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Filter Null: Do not filter any null images.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Exposure: Between -16% and +16%
Blur: Up to 2px
Noise: Up to 8% of pixels
Cutout: 4 boxes with 1% size each