System Information
- OS: OS X 10.13.3
- PyTorch version: 0.4.0a0+f6274a4
- How you installed PyTorch (conda, pip, source): source
- Python version: 3.6.4 (default, Jan 6 2018, 11:51:15)
- CUDA/cuDNN version: NA (On CPU)
- GPU models and configuration: NA (On CPU)
- GCC version (if compiling from source): Apple LLVM version 9.0.0 (clang-900.0.39.2)
Issue Information
I am trying to use nn.Bilinear without a bias, but doing so yields an error.
To reproduce the error run
import torch
import torch.nn as nn
m = nn.Bilinear(20, 30, 40, bias=False)
input1 = torch.randn(128, 20)
input2 = torch.randn(128, 30)
output = m(input1, input2)
This yields the error
(virtualenv) Kellys-MacBook-Pro:sprachspiel kdavis$ python test.py
Traceback (most recent call last):
File "test.py", line 7, in <module>
output = m(input1, input2)
File "/Users/kdavis/Code/mozilla/sprachspiel/virtualenv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 371, in __call__
result = self.forward(*input, **kwargs)
File "/Users/kdavis/Code/mozilla/sprachspiel/virtualenv/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 116, in forward
return F.bilinear(input1, input2, self.weight, self.bias)
File "/Users/kdavis/Code/mozilla/sprachspiel/virtualenv/lib/python3.6/site-packages/torch/nn/functional.py", line 1004, in bilinear
return torch._C._VariableFunctions.bilinear(input1, input2, weight, bias)
RuntimeError: dim() called on undefined TensorHowever, running
import torch
import torch.nn as nn
m = nn.Bilinear(20, 30, 40, bias=True)
input1 = torch.randn(128, 20)
input2 = torch.randn(128, 30)
output = m(input1, input2)
works fine.
System Information
Issue Information
I am trying to use
nn.Bilinearwithout a bias, but doing so yields an error.To reproduce the error run
This yields the error
However, running
works fine.