jinqiu

> Thanks very much for your help. According to this [rpautrat/SuperPoint#164](https://github.com/rpautrat/SuperPoint/issues/164), I comment the following three lines: > > https://github.com/shaofengzeng/SuperPoint-Pytorch/blob/6e5c6587311cd4f98f9a5b61e84731555778c958/solver/loss.py#L126 > > ``` > dot_product_desc = F.relu(dot_product_desc) > > ##l2_normalization...

> > > Thanks very much for your help. According to this [rpautrat/SuperPoint#164](https://github.com/rpautrat/SuperPoint/issues/164), I comment the following three lines: > > > https://github.com/shaofengzeng/SuperPoint-Pytorch/blob/6e5c6587311cd4f98f9a5b61e84731555778c958/solver/loss.py#L126 > > > > > > ```...

> > Thanks very much for your help. According to this [rpautrat/SuperPoint#164](https://github.com/rpautrat/SuperPoint/issues/164), I comment the following three lines: > > https://github.com/shaofengzeng/SuperPoint-Pytorch/blob/6e5c6587311cd4f98f9a5b61e84731555778c958/solver/loss.py#L126 > > ``` > dot_product_desc = F.relu(dot_product_desc) > >...

> > > > > > > > > > > Thanks very much for your help. According to this [rpautrat/SuperPoint#164](https://github.com/rpautrat/SuperPoint/issues/164), I comment the following three lines: > > >...

> @ericzzj1989 @jinqiua hi, I met the same descriptor loss. Have you figured out the reason? ”dot_product_desc“ does not need to do normalization, please refer to my last comment.

> > can fixed with this patch > > ``` > > diff --git a/python/tvm/relax/frontend/torch/fx_translator.py b/python/tvm/relax/frontend/torch/fx_translator.py > > index fde31af60..392ff2b39 100644 > > --- a/python/tvm/relax/frontend/torch/fx_translator.py > > +++ b/python/tvm/relax/frontend/torch/fx_translator.py >...