easy bin picking Computer Vision Model
Some images failed during generation
92 images (39%) failed to generate. The result of this training run may be different from others. We recommend regenerating the version and contact support if the issue persists.
141 Total Images
View All Images
Dataset Split
Train Set 145%
204Images
Valid Set 13%
19Images
Test Set 7%
10Images
Preprocessing
Auto-Orient: Applied
Auto-Adjust Contrast: Using Contrast Stretching
Random Sample: Include 100% train, 100% valid, 100% test
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Applied
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%
Noise: Up to 1% of pixels
Cutout: 3 boxes with 10% size each
Mosaic: Applied
Motion Blur: Length 20px, Angle: 0°, Frames: 1
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Noise: Up to 0.1% of pixels