wu-ruijie
commented
6 years ago I test your code； with the Theano backend, your code work well python: 0.09988655 0.10504469 0.10044335 0.10128921 0.09823733 0.095519 0.09941912 0.10130119 0.09886824 0.09999127 c++: 0.0998865515 0.105044685 0.100443356 0.101289213 0.0982373282 0.0955190063 0.0994191244 0.101301186 0.0988682434 0.0999912620
with the Tensorflow backend,sorry, it's incorrect python: 0.0998288 0.10554188 0.09975836 0.10162295 0.09870712 0.09481214 0.0988815 0.10205296 0.09908297 0.0997113 c++: 0.0998295173 0.105537765 0.0997576788 0.101601161 0.0986871123 0.0948245302 0.0989128724 0.102043636 0.0990825072 0.0997231528
if train more epochs, the difference greater with the Tensorflow backend
thanks your codes
pplonski
hello! I am using Keras2 and there is a compatibility problem due to conv2d layer which was changed in current version of Keras. Actually, the way it is stored in json file has also changed and as a result the current c++ code does not work as it is.
I made some changes in the code that I attach and now it works, however c++ and python do not provide the same results when conv2d is used. (If these two conv2D layers are omitted the results are the same) Even though the two outcomes are comparable, there are not the same so I would like to ask you if there is something more that needs to be changed.
The main change is the following: in keras1.x convolutiond2D layer's weights are stored and their shape is [nb_filter][depth][row][cols], which gives for the first layer of the example the numbers [4][1][3][3] In contrary, in Keras 2.x conv2D layer's weights are stored and their shape is now [row][cols][depth][nb_filters], which gives the numbers [3][3][1][4] (you can see this in the dumped file created). So, in order to use current cpp I created m_rowsVec() in class keras::LayerConv2D : public Layer. Then, I read the weights from dumped file and i store them there. Afterwards I make the transition to the old format and I store them in m_kernels(). (see lines 71 - 111 in keras_model.cc). The following code remains the same.
The code attached works fine for new Keras2.0.6 but the prediction results are not the same as when I run them in python. Any suggestions? Should they be the same? keras2cpp(keras2 version).zip