prevision_quantum_nn.models.pennylane_backend.qnn_pennylane
¶
Pennylane module contains the base class of quantum neural networks based on pennylane
Module Contents¶
Classes¶
Class PennylaneNeuralNetwork. |
-
prevision_quantum_nn.models.pennylane_backend.qnn_pennylane.
OPTIMIZER_NAMES
= ['SGD', 'Adagrad', 'Adam', 'RMSProp']¶
-
class
prevision_quantum_nn.models.pennylane_backend.qnn_pennylane.
PennylaneNeuralNetwork
(params)¶ Bases:
prevision_quantum_nn.models.qnn.QuantumNeuralNetwork
Class PennylaneNeuralNetwork.
-
params
¶ dictionary containing the main parameters of the model
- Type
dict
-
optimizer
¶ Optimizer of the quantum circuit. Can be AdamOptimizer or NesterovMomentumOptimizer
- Type
Optimizer
-
batch_size
¶ size of the batch with which the training should be perfomed
- Type
int
-
verbose
¶ sets the verbosity to on if True and off if False
- Type
bool
-
interface
¶ interface of the pennylane backend. Can be tf or autograd
- Type
str
-
learning_rate
¶ learning rate at which the fitting phase needs to be performed
-
encode_data
(self, x)¶ needs to be overridden by child class
-
layer
(self, v)¶ needs to be overridden by child class
-
output_layer
(self, v)¶ needs to be overridden by child class
-
neural_network
(self, var, features=None)¶ Main method that is decorated by the qml.qnode decorator. This will set the structure of the neural network
-
cost
(self, var, features, labels)¶ cost function to be optimized
-
abstract
initialize_weights
(self, weights_file=None)¶ initialize weights
to be implemented depending on the architecture used
-
build
(self, weights_file=None)¶ builds the optimizer and initializes weights
-
build_optimizer
(self)¶ Builds the optimizer according to its name and to the interface used.
-
snapshot
(self, is_best=False)¶ Snapshots the model to a file.
-
load_weights
(self, weights_file)¶ Loads weights from file.
- Parameters
weights_file (string) – file name containing the weights
-
cost
(self, var, features, labels)¶ Cost to be optimized during training.
- Parameters
var (list) – weights of the model
features (array) – obervations to be evalueated by the model
labels (array) – labels associated to features
- Returns
- float
loss of the model given x
- Return type
loss
-
step
(self, features, labels, var)¶ Performs one step of training.
- Parameters
features (array) – observations
labels (array) – labels
var (array) – weights of the model
-
fit
(self, train_features, train_labels, plotter_callback, val_features=None, val_labels=None, verbose=True)¶ Fits data with model.
- Parameters
train_features (array) – training features
train_labels (array) – training labels
val_features (array) – validation features
val_labels (array) – validation labels
verbose (bool) – if True, verbosity will be activated
-
predict
(self, features)¶ Predicts certain obervations.
- Parameters
features (array) – observations to be predicted
- Returns
- float or int
prediction of the model
- Return type
preds
-
predict_proba
(self, features)¶ - Predicts the probabilities of a prediction for an
array of features
- Parameters
features (array) – features to be predicted
- Returns
- float or int
prediction of the model
- Return type
preds
-