RuntimeError: Subtraction, the `-` operator, with a bool tensor is not supported. If you are trying to invert a mask, use the `~` or `logical_not()` operator instead. about i2l-meshnet_release HOT 6 CLOSED

Ah.. this is because of torchgeometry do not update their kernel code according to the updated pytorch kernel code. I'll add some hacks that I tried in README. Basically, you need to change L301~L304 of anaconda3/lib/python3.8/site-packages/torchgeometry/core/conversion.py to below.

mask_c0 = mask_d2.float() * mask_d0_d1.float()
mask_c1 = mask_d2.float() * (1 - mask_d0_d1.float())
mask_c2 = (1 - mask_d2.float()) * mask_d0_nd1.float()
mask_c3 = (1 - mask_d2.float()) * (1 - mask_d0_nd1.float())

It just changes binary masks to floating masks.

from i2l-meshnet_release.

@pablovela5620 This issue occurs due to torch version 1.2 or higher. On downgrading to torch==1.1, this issue gets resolved for me.

from i2l-meshnet_release.

Didn't get to try downgrading pytorch, but @mks0601 suggestion worked for me! Though probably not ideal, thank you both for the help!

from i2l-meshnet_release.

@pablovela5620 This issue occurs due to torch version 1.2 or higher. On downgrading to torch==1.1, this issue gets resolved for me.

Hello, I make torch==1.1, but there is a problem with "from contextlib import nullcontext" in the model.py file, "ImportError: cannot import name'nullcontext'", do you know how to solve it，thank you.

from i2l-meshnet_release.

@booker-max I am not sure about this error. But trying the below code by mka should work.

Ah.. this is because of torchgeometry do not update their kernel code according to the updated pytorch kernel code. I'll add some hacks that I tried in README. Basically, you need to change L301~L304 of anaconda3/lib/python3.8/site-packages/torchgeometry/core/conversion.py to below.

mask_c0 = mask_d2.float() * mask_d0_d1.float()
mask_c1 = mask_d2.float() * (1 - mask_d0_d1.float())
mask_c2 = (1 - mask_d2.float()) * mask_d0_nd1.float()
mask_c3 = (1 - mask_d2.float()) * (1 - mask_d0_nd1.float())

It just changes binary masks to floating masks.

from i2l-meshnet_release.

https://stackoverflow.com/questions/45187286/how-do-i-write-a-null-no-op-contextmanager-in-python

The nullcontext can be used in Python 3.7

from i2l-meshnet_release.