Dataset Versions
v2
V2_projet
Generated on Feb 1, 2024
64 Total Images
View All ImagesDataset Split
Train Set 75%
48Images
Valid Set 13%
8Images
Test Set 13%
8Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 128x128
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Blur: Up to 2.5px
Noise: Up to 1.52% of pixels
Cutout: 5 boxes with 10% size each