theanets.recurrent.Autoencoder¶
-
class
theanets.recurrent.
Autoencoder
(layers, loss='mse', weighted=False)¶ An autoencoder network attempts to reproduce its input.
Notes
Autoencoder models default to a
MSE
loss. To use a different loss, provide a non-default argument for theloss
keyword argument when constructing your model.Examples
To create a recurrent autoencoder, just create a new model instance. Often you’ll provide the layer configuration at this time:
>>> model = theanets.recurrent.Autoencoder([10, (20, 'rnn'), 10])
See Creating a Model for more information.
Data
Training data for a recurrent autoencoder takes the form of a three-dimensional array. The shape of this array is (num-examples, num-time-steps, num-variables): the first axis enumerates data points in a batch, the second enumerates time steps, and the third enumerates the variables in the model.
For instance, to create a training dataset containing 1000 examples, each with 100 time steps:
>>> inputs = np.random.randn(1000, 100, 10).astype('f')
Training
Training the model can be as simple as calling the
train()
method:>>> model.train([inputs])
See Training a Model for more information.
Use
A model can be used to
predict()
the output of some input data points:>>> test = np.random.randn(3, 200, 10).astype('f') >>> print(model.predict(test))
Note that the test data does not need to have the same number of time steps as the training data.
Additionally, autoencoders can
encode()
a set of input data points:>>> enc = model.encode(test)
See Using a Model for more information.
-
__init__
(layers, loss='mse', weighted=False)¶
Methods
Attributes
DEFAULT_OUTPUT_ACTIVATION
INPUT_NDIM
inputs
A list of Theano variables for feedforward computations. num_params
Number of parameters in the entire network model. params
A list of the learnable Theano parameters for this network. variables
A list of Theano variables for loss computations. -