Question about large memory usage when calculating chamfer distance with KDTree

[dc3505]

When we try to reproduce the experiment result, it seems we have a peak memory usage when trying to calculate chamfer distance with KDTree. We are using a mesh ~2M with ~50k vertices, but get ~250G memory usage for this and cause a out of memory issue. Is this an expected behavior?

Thanks again for your help!

[Zvyozdo4ka]

how did you set conda env ? i don't get why the documentation always lacks of correct information, maybe it is deliberately, to make it fail others. Here is original environment.yml:

I changed it to this:

and it is already more 3 hours while:

when i installed through pip the libraries from environment.yml, i can't run sample: