RuntimeError: invalid argument 0: Tensors must have same number of dimensions: got 3 and 2 about ncrfpp HOT 9 CLOSED

I just add one line partition = partition.view(partition.size()[0], partition.size()[1], 1)in function _viterbi_decode in the for loop,now it can run,thank you very much.

from ncrfpp.

partition = partition.unsqueeze(-1) works also.

from ncrfpp.

partition = partition.unsqueeze(-1) works also.

Your method is not working.

from ncrfpp.

Hi @Charleyfeng , I am not sure about where the problem is based on this simple error message. If you use the correct data input, I guess the problem may be caused by the version of PyTorch. Please make sure you use the PyTorch 0.3.0

If you are using right version, then further debug is needed.

from ncrfpp.

My torch version is 0.3.1.post2.

from ncrfpp.

Then you may seperate the error sentence into several lines to see where does this error message come from (I guess it comes from function cat or view). Then for the error function, you may check its input shape and output shape to see if they are compatible

from ncrfpp.

Ok,Thank you,I will check what you have mentioned,and if any result,I will post here.

from ncrfpp.

cool!

from ncrfpp.

Hi sir,
I'm student learning ML/DL.
Today, I got a same error msg from my torch code.
Could you plz tell me what's the code file belongs to this issue?

from ncrfpp.