deepupe_tensorflow The smoothness loss is also different: I kept getting nan with the logarithmic operation so I deleted that part, the left part could be seen as total-variation loss (tv-loss)

The smoothness loss is also different: I kept getting nan with the logarithmic operation so I deleted that part, the left part could be seen as total-variation loss (tv-loss)

Open lilin-git opened this issue 6 years ago • 1 comments

You normalize the data in (-1,1) and the parameter of tf. log () is greater than 0, so loss is nan.

Jul 31 '19 09:07 lilin-git

sorry for late reply, i also found this problem in my training. I suggest you to try deep guided filter as it only use tensorflow default ops and no additional self-defined layers. I got good result with it

Oct 24 '19 09:10 SystemErrorWang

deepupe_tensorflow deepupe_tensorflow copied to clipboard

The smoothness loss is also different: I kept getting nan with the logarithmic operation so I deleted that part, the left part could be seen as total-variation loss (tv-loss)

deepupe_tensorflow
deepupe_tensorflow copied to clipboard