Dataset Versions
Versions
v1
2023-05-28 12:02am
Generated on May 27, 2023
274 Total Images
View All Images
Dataset Split
Train Set 88%
240Images
Valid Set 8%
23Images
Test Set 4%
11Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 31% Maximum Zoom
Shear: ±6° Horizontal, ±37° Vertical
Grayscale: Apply to 36% of images
Brightness: Between -21% and +21%
Blur: Up to 2px
Noise: Up to 7% of pixels
Cutout: 12 boxes with 18% size each