SDP2-CNN Computer Vision Dataset
2142 Total Images
View All Images
Dataset Split
Train Set 87%
1872Images
Valid Set 9%
180Images
Test Set 4%
90Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Cutout: 3 boxes with 10% size each