Skunk_works_Halcyon Computer Vision Model
byPoly6Task:
Instance Segmentation
Versions
3008 Total Images
View All Images
Dataset Split
Train Set 97%
2905Images
Valid Set 2%
69Images
Test Set 1%
34Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 5
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Exposure: Between -14% and +14%
Noise: Up to 0.14% of pixels