Dataset Versions

v1

2024-01-15 7:17pm

Generated on Jan 15, 2024

Dataset Split

Train Set 93%
2436Images
Valid Set 3%
90Images
Test Set 3%
83Images

Preprocessing

Auto-Orient: Applied
Isolate Objects: Applied
Dynamic Crop: Class: Biodegradable
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Noise: Up to 0.1% of pixels