as_matrix problem

[YoungJ-Baek]

Hi, I'm working on your previous code because of the same problem with
'#19 (comment)'

But I have problem with this issue
Traceback (most recent call last): File "demo.py", line 111, in <module> theta_aff = model_aff(batch) File "/home/youngj/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/home/youngj/Desktop/cnngeometric_pytorch-4b9a5b7eedce503199a03147de2115ffe0444888/model/cnn_geometric_model.py", line 156, in forward theta = self.FeatureRegression(correlation) File "/home/youngj/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/home/youngj/Desktop/cnngeometric_pytorch-4b9a5b7eedce503199a03147de2115ffe0444888/model/cnn_geometric_model.py", line 110, in forward x = x.view(x.size(0), -1) RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

I think this is because I change as_matrix to to_numpy and values because as_matrix has been deprecated.
If you know solution of this problem, plz reply