About Correlation layer and can you share me the code without deformable conv

[yanzhou-li]

i come back again. Drive into the theme,I want to know if I use the concatand convolution instead of correlation,the net can work? if it works, how can I do that,thanks!
@haofeixu @Ilya-Muromets

[haofeixu]

@yanzhou-li , yes, our implementation supports both cost volume construction methods, you can check the --feature_similarity argument in train.py.

[haofeixu]

BTW, if you don't want to use the deformable conv, you can set the --num_deform_blocks to 0 in train.py.

[yanzhou-li]

@haofeixu i got it. thank you