Zhixin Wang

icon indicating an email [email protected]

icon company South China University of Technology icon location Guangzhou,China

Results 1 issues of Zhixin Wang

Can't understand the backward of mask_output.

3 comment

After sigmoid operator, the mask loss should be binary cross-entropy loss but ignore the loss of background mask. But in the code, https://github.com/TuSimple/mx-maskrcnn/blob/c866544cb2ab93f868bce004e86af7a93451d977/rcnn/PY_OP/mask_output.py#L27 In common, it will like ` (...