RuntimeError torch related

[Jaykob]

Hi!
Thanks for sharing your code with us! :-)
I'm trying to train the model using ex1_train.sh with the ModelNet40.
After a long time of training the script quit with the following error:

.../ptlk/pointlk.py", line 58, in do_forward
    a0[:, 0:3, 3] = p0_m
RuntimeError: unsupported operation: more than one element of the written-to tensor refers to a single memory location. Please clone() the tensor before performing the operation.

Can you help me find out what's going wrong here?

[DavidBoja]

As the error says, you can clone the tensors using the .clone() method.
Add it to lines 54 and 55 of the pointlk.py script as so:

a0 = torch.eye(4).view(1, 4, 4).expand(p0.size(0), 4, 4).to(p0).clone() # [B, 4, 4]
a1 = torch.eye(4).view(1, 4, 4).expand(p1.size(0), 4, 4).to(p1).clone() # [B, 4, 4]