> > > > @xwmeng, We now can support 3 padding options for conv layer. > > - valid: the same definition as TF model. (the size of feature map > > changed). > > - same: the same definition as TF model. (zero filled for outside pixels). > > - same_clamp_to_edge: just like 'same' option, but edge filled for outside > pixels. So we don't need change SR code for the padding. > > I think as long as we add different padding options, we need to change the SR > generate code. > >
yes, you are right. Sorry for not made it clear, I meant that the key logic/code for padding does not change. We have to add code to export the value of the pad option into SR native model, no matter which method used. _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
