墙体识别改进3 Computer Vision Dataset
Versions
9356 Total Images
View All Images
Dataset Split
Train Set 92%
8631Images
Valid Set 4%
359Images
Test Set 4%
366Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Exposure: Between -15% and +15%
Blur: Up to 3px