CODEWITHSUNDEEP
pythontheanokeras
cubeception
cubeception

Reputation: 164

Keras/Theano output

I'm struggling with theano types.

I created some Sequential model in Keras, where the last layer is

final_model.add(Dense(1, activation='sigmoid'))

When I try

final_model.get_output([x,x])
>>> sigmoid.0

How can I get get the actual output number? I tried using output.eval() resp. output[0][0].eval() but that results only in

theano.gof.fg.MissingInputError: ("An input of the graph, used to compute Shape(<TensorType(int32, matrix)>), was not provided and not given a value.Use the Theano flag exception_verbosity='high',for more information on this error.", <TensorType(int32, matrix)>)

Upvotes: 1

Views: 94

Answers (1)

Dr. Snoopy
Dr. Snoopy

Reputation: 56367

Don't drown on a glass of water.

You can just use final_model.predict(input) to get an array of predictions, given an array of input values. Just note that this function can be used to predict more than set of input values.

Upvotes: 2

Related Questions