Closed XiaoqiangZhou closed 3 years ago
Hi, for this part, you can refer to this project https://www.kernel-operations.io/geomloss/ and its code https://github.com/jeanfeydy/geomloss. I will also add acknowledgment to this project in the end.
@fnzhan Thanks for your reply.
Besides, could you please point out the detailed place you implement the optimal transport in your code. e.g., the inference process (Equ. 1 to 5 in paper) and loss supervision (Equ. 8 in paper)? I find many OT examples in the util
folder, but they are not used in the main training/testing code.
@fnzhan Thanks for your reply.
Besides, could you please point out the detailed place you implement the optimal transport in your code. e.g., the inference process (Equ. 1 to 5 in paper) and loss supervision (Equ. 8 in paper)? I find many OT examples in the
util
folder, but they are not used in the main training/testing code.
The implementation can be found in https://github.com/fnzhan/UNITE/tree/main/models/networks/geomloss , and 245-299 in https://github.com/fnzhan/UNITE/blob/main/models/networks/correspondence.py . The loss is consistent with CoCosNet. The OT examples in util have no relation with the implementation of this work, just ignore it.
@fnzhan Thanks for your quick reply~
245-299 in https://github.com/fnzhan/UNITE/blob/main/models/networks/correspondence.py
This guidance really helps me a lot. Thanks!
Thanks for sharing such a great work and releasing the codes.
I have a question about the implementation of
log_sinkhorn
function insinkhorn.py
. Is it should bev = eps * (a + min_eps(u, v, dim=1)) + v
instead ofv = eps * min_eps(u, v, dim=1) + v
in Line 57?It would be better if you can give a link to the official implementation for this part.
Thanks.