Open UcanSee opened 5 years ago
I want to train pspnet on my own dataset, but I don't know how to calculate the loss because there are two outputs x and x_aux when training, the x_aux is not same size with the input, how should i calculate the loss?
I want to train pspnet on my own dataset, but I don't know how to calculate the loss because there are two outputs x and x_aux when training, the x_aux is not same size with the input, how should i calculate the loss?