annotation cellule Computer Vision Model
360 Total Images
View All Images
Dataset Split
Train Set 86%
309Images
Valid Set 10%
35Images
Test Set 4%
16Images
Preprocessing
Tile: 2 rows x 2 columns
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Grayscale: Applied
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -11° and +11°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 4px
Noise: Up to 5.01% of pixels
Cutout: 3 boxes with 16% size each