theanets.feedforward.Classifier

class theanets.feedforward.Classifier(layers, loss='xe', weighted=False, rng=13)

A classifier computes a distribution over labels, given an input.

Notes

Classifier models default to a cross-entropy loss. To use a different loss, provide a non-default argument for the loss keyword argument when constructing your model.

Examples

To create a classification model, just create a new class instance. Often you’ll provide the layer configuration at this time:

>>> model = theanets.Classifier([10, (20, 'tanh'), 50])

See Creating a Model for more information.

Data

Training data for a classification model takes the form of a two-dimensional array of input data and a one-dimensional vector of target labels. The input array has a shape (num-examples, num-variables): the first axis enumerates data points in a batch, and the second enumerates the input variables in the model.

The second array provides the target class labels for the inputs. Its shape is (num-examples, ), and each integer value in the array gives the class label for the corresponding input example.

For instance, to create a training dataset containing 1000 examples:

>>> inputs = np.random.randn(1000, 10).astype('f')
>>> outputs = np.random.randint(50, size=1000).astype('i')

Training

Training the model can be as simple as calling the train() method, giving the inputs and target outputs as a dataset:

>>> model.train([inputs, outputs])

See Training a Model for more information.

Use

A classification model can be used to predict() the output of some input data points:

>>> test = np.random.randn(3, 10).astype('f')
>>> print(model.predict(test))

This method returns a vector containing the most likely class for each input example.

To retrieve the probabilities of the classes for each example, use predict_proba():

>>> model.predict_proba(test).shape
(3, 50)

See also Using a Model for more information.

__init__(layers, loss='xe', weighted=False, rng=13)

x.__init__(…) initializes x; see help(type(x)) for signature

Methods

__init__(layers[, loss, weighted, rng])	x.__init__(…) initializes x; see help(type(x)) for signature
add_layer([layer])	Add a layer to our network graph.
add_loss([loss])	Add a loss function to the model.
build_graph([regularizers])	Connect the layers in this network to form a computation graph.
classify(x, **kwargs)
feed_forward(x, **kwargs)	Compute a forward pass of all layers from the given input.
find(which, param)	Get a parameter from a layer in the network.
itertrain(train[, valid, algo, subalgo, …])	Train our network, one batch at a time.
load(filename_or_handle)	Load a saved network from disk.
loss(**kwargs)	Return a variable representing the regularized loss for this network.
monitors(**kwargs)	Return expressions that should be computed to monitor training.
predict(x, **kwargs)	Compute a greedy classification for the given set of data.
predict_logit(x, **kwargs)	Compute the logit values that underlie the softmax output.
predict_proba(x, **kwargs)	Compute class posterior probabilities for the given set of data.
save(filename_or_handle)	Save the state of this network to a pickle file on disk.
score(x, y[, w])	Compute the mean accuracy on a set of labeled data.
set_loss(*args, **kwargs)	Clear the current loss functions from the network and add a new one.
train(*args, **kwargs)	Train the network until the trainer converges.
updates(**kwargs)	Return expressions to run as updates during network training.

Attributes

DEFAULT_OUTPUT_ACTIVATION	Default activation for the output layer.
INPUT_NDIM
OUTPUT_NDIM	Number of dimensions for holding output data arrays.
inputs	A list of Theano variables for feedforward computations.
params	A list of the learnable Theano parameters for this network.
variables	A list of Theano variables for loss computations.

DEFAULT_OUTPUT_ACTIVATION = 'softmax'

Default activation for the output layer.

OUTPUT_NDIM = 1

Number of dimensions for holding output data arrays.

monitors(**kwargs)

Return expressions that should be computed to monitor training.

Returns:

monitors : list of (name, expression) pairs

A list of named monitor expressions to compute for this network.

predict(x, **kwargs)

Compute a greedy classification for the given set of data.

Parameters:

x : ndarray (num-examples, num-variables)

An array containing examples to classify. Examples are given as the rows in this array.

Returns:

k : ndarray (num-examples, )

A vector of class index values, one per row of input data.

predict_logit(x, **kwargs)

Compute the logit values that underlie the softmax output.

Parameters:

x : ndarray (num-examples, num-variables)

An array containing examples to classify. Examples are given as the rows in this array.

Returns:

l : ndarray (num-examples, num-classes)

An array of posterior class logit values, one row of logit values per row of input data.

predict_proba(x, **kwargs)

Compute class posterior probabilities for the given set of data.

Parameters:

x : ndarray (num-examples, num-variables)

An array containing examples to predict. Examples are given as the rows in this array.

Returns:

p : ndarray (num-examples, num-classes)

An array of class posterior probability values, one per row of input data.

score(x, y, w=None, **kwargs)

Compute the mean accuracy on a set of labeled data.

Parameters:

x : ndarray (num-examples, num-variables)

An array containing examples to classify. Examples are given as the rows in this array.

y : ndarray (num-examples, )

A vector of integer class labels, one for each row of input data.

w : ndarray (num-examples, )

A vector of weights, one for each row of input data.

Returns:

score : float

The (possibly weighted) mean accuracy of the model on the data.