Closed Pooja-Palod closed 6 years ago
Why do not i have _time_distributed_dense module from keras.layers.recurrent? Please answer it if you have free time,thank you!
Probably a different Keras version, try Keras 2 branch: https://github.com/zygmuntz/pointer-networks-experiments/tree/keras-2.0
File "test.py", line 82, in
print "categorical accuracy: ", categorical_accuracy( YY_test, p ).eval()
File "/usr/local/lib/python2.7/dist-packages/keras/metrics.py", line 10, in categorical_accuracy
return K.mean(K.equal(K.argmax(y_true, axis=-1),
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 523, in argmax
axis = axis % len(x.get_shape())
AttributeError: 'numpy.ndarray' object has no attribute 'get_shape'