Under Tensorflow 1.14, RBF layer cannot be reloaded after being saved

[ljcwang]

I was trying to reload the model after saving it. I used the same code as the test.py and the command for saving is the same as what you posted. The tensorflow version is 1.14.0 and Keras-application is 1.0.8. Thank you for your help!

The error message is as following:
`rbfnet = load_model("test_rbf.h5", custom_objects={'RBFLayer': RBFLayer})
~\anaconda3\lib\site-packages\tensorflow\python\framework\tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape, allow_broadcast)
560 raise TypeError("Failed to convert object of type %s to Tensor. "
561 "Contents: %s. Consider casting elements to a "
--> 562 "supported type." % (type(values), values))
563 tensor_proto.string_val.extend(str_values)
564 return tensor_proto

TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (10, Dimension(1)). Consider casting elements to a supported type.
`

[PetraVidnerova]

Thanks. I will look at it and let you know as soon as possible.

[PetraVidnerova]

I am not able to repreduce error, getting another one instead. I will have to try anaconda. Sorry for the inconvenience.