You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Initially running the python train.py command the warning/error message that pops up is: 2017-12-04 12:12:56,759 WARNING /root/repos/tensorflow/bazel-bin/tensorflow/core/user_ops/sparse_conv2d.so: cannot open shared object file: Permission denied with the accompanying error message AttributeError: 'LookupAlignConvolution2d' object has no attribute '_convolution_op'.
Once you give permission to the that file path (assuming you can because we had to give root privileges to each individual path) the warning disappears but the error message stays. Further investigation shows that it could be an issue with the tensorflow version but even running tensorflow 1.3 there is still an issue. The project itself has some issues. Any help would be appreciated! Thanks in advance!
The text was updated successfully, but these errors were encountered:
So to anyone who runs into this issue the way to fix it would be to add the lines: self._convolution_op = nn_ops.Convolution( input_shape, filter_shape=self.kernel.get_shape(), dilation_rate=self.dilation_rate, strides=self.strides, padding=self.padding.upper(), data_format=utils.convert_data_format(self.data_format, self.rank + 2))
into the LookupAlignConvolution2d.py. Put the line of code in between these two lines of code in the .py file and it should work: self.input_spec = base.InputSpec(ndim=self.rank + 2, axes={channel_axis: input_dim}) self.built = True
Initially running the python train.py command the warning/error message that pops up is:
2017-12-04 12:12:56,759 WARNING /root/repos/tensorflow/bazel-bin/tensorflow/core/user_ops/sparse_conv2d.so: cannot open shared object file: Permission denied
with the accompanying error messageAttributeError: 'LookupAlignConvolution2d' object has no attribute '_convolution_op'
.Once you give permission to the that file path (assuming you can because we had to give root privileges to each individual path) the warning disappears but the error message stays. Further investigation shows that it could be an issue with the tensorflow version but even running tensorflow 1.3 there is still an issue. The project itself has some issues. Any help would be appreciated! Thanks in advance!
The text was updated successfully, but these errors were encountered: