Closed Perseus14 closed 7 years ago
While running the code _make_keras_charnetmodel.py, I encountered the error "'TensorVariable' object has no attribute '_keras_shape'".
I had followed the instructions given in the README doc on overwriting convolution.py and _theanobackend.py
Apparently, the error in encountered in line 43
model.add(Convolution2D(nb_filters[layer1], nb_conv[layer1], nb_conv[layer1],weights=weights,input_shape=(1, img_rows,img_cols),activation='relu',border_mode='same'))
Image is attached below
My keras and theano versions were different. Once I installed the required version. It worked
Thanks for closing. This is what I was going to suggest.
While running the code _make_keras_charnetmodel.py, I encountered the error "'TensorVariable' object has no attribute '_keras_shape'".
I had followed the instructions given in the README doc on overwriting convolution.py and _theanobackend.py
Apparently, the error in encountered in line 43
model.add(Convolution2D(nb_filters[layer1], nb_conv[layer1], nb_conv[layer1],weights=weights,input_shape=(1, img_rows,img_cols),activation='relu',border_mode='same'))
Image is attached below