Dataset Versions
v1
syringe_dirty_clean_dataset_20_08_2021
Generated on Aug 20, 2021
1440 Total Images
View All Images
Dataset Split
Train Set 88%
1260Images
Valid Set 8%
120Images
Test Set 4%
60Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 416x416
Grayscale: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±15° Horizontal, ±15° Vertical
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels
Cutout: 3 boxes with 10% size each