Dataset Versions

v22

2023-09-13 1:11am

Generated on Sep 13, 2023

Dataset Split

Train Set 87%
19302Images
Valid Set 9%
1924Images
Test Set 4%
958Images

Preprocessing

Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Modify Classes: 14 remapped, 5 dropped

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Grayscale: Apply to 11% of images
Brightness: Between -25% and +25%
Blur: Up to 3.75px
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Noise: Up to 5% of pixels

Similar Projects

See More
59 images 1 model