Dataset Versions
v1
2024-02-13 2:08am
Generated on Feb 12, 2024
3321 Total Images
View All Images
Dataset Split
Train Set 100%
3321Images
Valid Set %
0Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-100% Horizontal Region, 25-68% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 3 rows x 3 columns
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 27% Maximum Zoom
Saturation: Between -32% and +32%
Brightness: Between -23% and +23%
Exposure: Between -12% and +12%
Blur: Up to 3px
Noise: Up to 1.05% of pixels
Cutout: 11 boxes with 10% size each