Printing / saving autogenerators generated in Keras
I have this auto encoder:
input_dim = Input(shape=(10,)) encoded1 = Dense(30, activation = 'relu')(input_dim) encoded2 = Dense(20, activation = 'relu')(encoded1) encoded3 = Dense(10, activation = 'relu')(encoded2) encoded4 = Dense(6, activation = 'relu')(encoded3) decoded1 = Dense(10, activation = 'relu')(encoded4) decoded2 = Dense(20, activation = 'relu')(decoded1) decoded3 = Dense(30, activation = 'relu')(decoded2) decoded4 = Dense(ncol, activation = 'sigmoid')(decoded3) autoencoder = Model(input = input_dim, output = decoded4) autoencoder.compile(-...) autoencoder.fit(...)
Now I would like to print or save the functions generated in encoding4. Basically, starting with a huge dataset, I would like to extract the functions generated by autoencoder after the tutorial part to get a limited view of my dataset.
could you help me?
source to share
You can do this by creating a "encoder" model:
encoder = Model(input = input_dim, output = encoded4)
This will use the same instances of layers that you trained with the autoencoder and should create this function if you use it in "output mode" like encoder.predict()
Hope this helps :)
source to share
So basically by creating code like this:
encoder = Model (input_dim,encoded4)
encoded_input=Input(shape=(6,))
and then using:
encoded_data=encoder.predict(data)
where the data in the function predict
is a dataset, the output is generated with
print encoded_data
is a limited view of my dataset.
Right?
thank
source to share