How to apply inferred mask to image
simonmelouah opened this issue · comments
Following along with the multiclass segmentation example, the model performs fairly well on a custom dataset however when I try to use the mask on the original image using OpenCV's bitwise_and function I get
error: OpenCV(4.8.0) [/Users/runner/work/opencv-python/opencv-python/opencv/modules/core/src/arithm.cpp:230](https://file+.vscode-resource.vscode-cdn.net/Users/runner/work/opencv-python/opencv-python/opencv/modules/core/src/arithm.cpp:230): error: (-215:Assertion failed) (mtype == CV_8U || mtype == CV_8S) && _mask.sameSize(*psrc1) in function 'binary_op'
Is there some post processing required to be able to use the inferred masks output by the trained model (apologies for the noise, have exhausted all possible other resources to try and figure it out)?