keras_shape and backend_shape mismatch with shape changing operation

[sandeep-krishnamurthy]

Here is the detailed bug report from the user - https://github.com/bgshin/mxnet_cnn/blob/master/src/bug.md

Summary of the issue:

• keras_shape and backend_shape doesn't match after applying shape changing operations. When performing an tensor operation (like multiplication), keras tries to check the validity of a given operation using keras_shape.
• If the shape of a tensor is changed by some operation (eg. slicing a tensor), then both of the keras_shape and backend_shape should be changed.
• However, for mxNet, only backend_shape is changed. This causes an error when applying an operations that requires correct shape information.

[lupesko]

+1

[sandeep-krishnamurthy]

Create PR for the fix - https://github.com/dmlc/keras/pull/84

[sandeep-krishnamurthy]

Please rebuild from latest master to get the fix.

$ git clone --recursive https://github.com/dmlc/keras $ cd keras $ python setup.py install --user

In the meantime, we will work on updating the pip package.