109 lines
5.3 KiB
Plaintext
109 lines
5.3 KiB
Plaintext
---
|
||
title: DiscriminativeNetwork
|
||
description: API reference for qiskit.aqua.components.neural_networks.DiscriminativeNetwork
|
||
in_page_toc_min_heading_level: 1
|
||
python_api_type: class
|
||
python_api_name: qiskit.aqua.components.neural_networks.DiscriminativeNetwork
|
||
---
|
||
|
||
<span id="qiskit-aqua-components-neural-networks-discriminativenetwork" />
|
||
|
||
# qiskit.aqua.components.neural\_networks.DiscriminativeNetwork
|
||
|
||
<Class id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork" isDedicatedPage={true} github="https://github.com/qiskit-community/qiskit-aqua/tree/stable/0.8/qiskit/aqua/components/neural_networks/discriminative_network.py" signature="DiscriminativeNetwork" modifiers="class">
|
||
Base class for discriminative Quantum or Classical Neural Networks.
|
||
|
||
This method should initialize the module but raise an exception if a required component of the module is not available.
|
||
|
||
### \_\_init\_\_
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork.__init__" signature="__init__()" modifiers="abstract">
|
||
Initialize self. See help(type(self)) for accurate signature.
|
||
</Function>
|
||
|
||
## Methods
|
||
|
||
| | |
|
||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
|
||
| [`__init__`](#qiskit.aqua.components.neural_networks.DiscriminativeNetwork.__init__ "qiskit.aqua.components.neural_networks.DiscriminativeNetwork.__init__")() | Initialize self. |
|
||
| [`get_label`](#qiskit.aqua.components.neural_networks.DiscriminativeNetwork.get_label "qiskit.aqua.components.neural_networks.DiscriminativeNetwork.get_label")(x) | Apply quantum/classical neural network to the given input sample and compute the respective data label |
|
||
| [`loss`](#qiskit.aqua.components.neural_networks.DiscriminativeNetwork.loss "qiskit.aqua.components.neural_networks.DiscriminativeNetwork.loss")(x, y\[, weights]) | Loss function used for optimization |
|
||
| [`set_seed`](#qiskit.aqua.components.neural_networks.DiscriminativeNetwork.set_seed "qiskit.aqua.components.neural_networks.DiscriminativeNetwork.set_seed")(seed) | Set seed. |
|
||
| [`train`](#qiskit.aqua.components.neural_networks.DiscriminativeNetwork.train "qiskit.aqua.components.neural_networks.DiscriminativeNetwork.train")(data, weights\[, penalty, …]) | Perform one training step w\.r.t to the discriminator’s parameters |
|
||
|
||
### get\_label
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork.get_label" signature="get_label(x)" modifiers="abstract">
|
||
Apply quantum/classical neural network to the given input sample and compute the respective data label
|
||
|
||
**Parameters**
|
||
|
||
**x** (*Discriminator*) – input, i.e. data sample.
|
||
|
||
**Raises**
|
||
|
||
**NotImplementedError** – not implemented
|
||
</Function>
|
||
|
||
### loss
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork.loss" signature="loss(x, y, weights=None)" modifiers="abstract">
|
||
Loss function used for optimization
|
||
|
||
**Parameters**
|
||
|
||
* **x** (*Discriminator*) – output.
|
||
* **y** (*Label*) – the data point
|
||
* **weights** (*numpy.ndarray*) – Data weights.
|
||
|
||
**Returns**
|
||
|
||
Loss w\.r.t to the generated data points.
|
||
|
||
**Raises**
|
||
|
||
**NotImplementedError** – not implemented
|
||
</Function>
|
||
|
||
### set\_seed
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork.set_seed" signature="set_seed(seed)" modifiers="abstract">
|
||
Set seed.
|
||
|
||
**Parameters**
|
||
|
||
**seed** (*int*) – seed
|
||
|
||
**Raises**
|
||
|
||
**NotImplementedError** – not implemented
|
||
</Function>
|
||
|
||
### train
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.DiscriminativeNetwork.train" signature="train(data, weights, penalty=False, quantum_instance=None, shots=None)" modifiers="abstract">
|
||
Perform one training step w\.r.t to the discriminator’s parameters
|
||
|
||
**Parameters**
|
||
|
||
* **data** (*numpy.ndarray*) – Data batch.
|
||
* **weights** (*numpy.ndarray*) – Data sample weights.
|
||
* **penalty** (*bool*) – Indicate whether or not penalty function is applied to the loss function. Ignored if no penalty function defined.
|
||
* **quantum\_instance** ([*QuantumInstance*](qiskit.aqua.QuantumInstance "qiskit.aqua.QuantumInstance")) – used to run Quantum network. Ignored for a classical network.
|
||
* **shots** (*int*) – Number of shots for hardware or qasm execution. Ignored for classical network
|
||
|
||
**Returns**
|
||
|
||
with Discriminator loss and updated parameters.
|
||
|
||
**Return type**
|
||
|
||
dict
|
||
|
||
**Raises**
|
||
|
||
**NotImplementedError** – not implemented
|
||
</Function>
|
||
</Class>
|
||
|