Trial Computer Vision Model
1525 Total Images
View All Images
Dataset Split
Train Set 98%
1500Images
Valid Set 1%
16Images
Test Set 1%
9Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Grayscale: Applied
Augmentations
Outputs per training example: 10
Shear: ±13° Horizontal, ±15° Vertical
Grayscale: Apply to 18% of images
Hue: Between -22° and +22°
Saturation: Between -28% and +28%
Brightness: Between -23% and +23%
Exposure: Between -11% and +11%
Blur: Up to 0.9px
Noise: Up to 1.21% of pixels