Closed yanzhou-li closed 3 years ago
@yanzhou-li , yes, our implementation supports both cost volume construction methods, you can check the --feature_similarity
argument in train.py
.
BTW, if you don't want to use the deformable conv, you can set the --num_deform_blocks
to 0 in train.py
.
@haofeixu i got it. thank you
i come back again. Drive into the theme,I want to know if I use the
concat
andconvolution
instead ofcorrelation
,the net can work? if it works, how can I do that,thanks! @haofeixu @Ilya-Muromets