144 lines
8.3 KiB
Plaintext
144 lines
8.3 KiB
Plaintext
---
|
||
title: NumPyDiscriminator
|
||
description: API reference for qiskit.aqua.components.neural_networks.NumPyDiscriminator
|
||
in_page_toc_min_heading_level: 1
|
||
python_api_type: class
|
||
python_api_name: qiskit.aqua.components.neural_networks.NumPyDiscriminator
|
||
---
|
||
|
||
<span id="qiskit-aqua-components-neural-networks-numpydiscriminator" />
|
||
|
||
# qiskit.aqua.components.neural\_networks.NumPyDiscriminator
|
||
|
||
<Class id="qiskit.aqua.components.neural_networks.NumPyDiscriminator" isDedicatedPage={true} github="https://github.com/qiskit-community/qiskit-aqua/tree/stable/0.8/qiskit/aqua/components/neural_networks/numpy_discriminator.py" signature="NumPyDiscriminator(n_features=1, n_out=1)" modifiers="class">
|
||
Discriminator based on NumPy
|
||
|
||
**Parameters**
|
||
|
||
* **n\_features** (`int`) – Dimension of input data vector.
|
||
* **n\_out** (`int`) – Dimension of the discriminator’s output vector.
|
||
|
||
### \_\_init\_\_
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.__init__" signature="__init__(n_features=1, n_out=1)">
|
||
**Parameters**
|
||
|
||
* **n\_features** (`int`) – Dimension of input data vector.
|
||
* **n\_out** (`int`) – Dimension of the discriminator’s output vector.
|
||
</Function>
|
||
|
||
## Methods
|
||
|
||
| | |
|
||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||
| [`__init__`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.__init__ "qiskit.aqua.components.neural_networks.NumPyDiscriminator.__init__")(\[n\_features, n\_out]) | **type n\_features**`int` |
|
||
| [`get_label`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.get_label "qiskit.aqua.components.neural_networks.NumPyDiscriminator.get_label")(x\[, detach]) | Get data sample labels, i.e. true or fake. |
|
||
| [`load_model`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.load_model "qiskit.aqua.components.neural_networks.NumPyDiscriminator.load_model")(load\_dir) | Load discriminator model |
|
||
| [`loss`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.loss "qiskit.aqua.components.neural_networks.NumPyDiscriminator.loss")(x, y\[, weights]) | Loss function :param x: sample label (equivalent to discriminator output) :type x: numpy.ndarray :param y: target label :type y: numpy.ndarray :param weights: customized scaling for each sample (optional) :type weights: numpy.ndarray |
|
||
| [`save_model`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.save_model "qiskit.aqua.components.neural_networks.NumPyDiscriminator.save_model")(snapshot\_dir) | Save discriminator model |
|
||
| [`set_seed`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.set_seed "qiskit.aqua.components.neural_networks.NumPyDiscriminator.set_seed")(seed) | Set seed. |
|
||
| [`train`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.train "qiskit.aqua.components.neural_networks.NumPyDiscriminator.train")(data, weights\[, penalty, …]) | Perform one training step w\.r.t to the discriminator’s parameters |
|
||
|
||
## Attributes
|
||
|
||
| | |
|
||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- |
|
||
| [`discriminator_net`](#qiskit.aqua.components.neural_networks.NumPyDiscriminator.discriminator_net "qiskit.aqua.components.neural_networks.NumPyDiscriminator.discriminator_net") | Get discriminator |
|
||
|
||
### discriminator\_net
|
||
|
||
<Attribute id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.discriminator_net">
|
||
Get discriminator
|
||
|
||
**Returns**
|
||
|
||
discriminator object
|
||
|
||
**Return type**
|
||
|
||
DiscriminatorNet
|
||
</Attribute>
|
||
|
||
### get\_label
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.get_label" signature="get_label(x, detach=False)">
|
||
Get data sample labels, i.e. true or fake.
|
||
|
||
**Parameters**
|
||
|
||
* **x** (*numpy.ndarray*) – Discriminator input, i.e. data sample.
|
||
* **detach** (*bool*) – depreciated for numpy network
|
||
|
||
**Returns**
|
||
|
||
Discriminator output, i.e. data label
|
||
|
||
**Return type**
|
||
|
||
numpy.ndarray
|
||
</Function>
|
||
|
||
### load\_model
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.load_model" signature="load_model(load_dir)">
|
||
Load discriminator model
|
||
|
||
**Parameters**
|
||
|
||
**load\_dir** (*str*) – file with stored pytorch discriminator model to be loaded
|
||
</Function>
|
||
|
||
### loss
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.loss" signature="loss(x, y, weights=None)">
|
||
Loss function :param x: sample label (equivalent to discriminator output) :type x: numpy.ndarray :param y: target label :type y: numpy.ndarray :param weights: customized scaling for each sample (optional) :type weights: numpy.ndarray
|
||
|
||
**Returns**
|
||
|
||
loss function
|
||
|
||
**Return type**
|
||
|
||
float
|
||
</Function>
|
||
|
||
### save\_model
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.save_model" signature="save_model(snapshot_dir)">
|
||
Save discriminator model
|
||
|
||
**Parameters**
|
||
|
||
**snapshot\_dir** (*str*) – directory path for saving the model
|
||
</Function>
|
||
|
||
### set\_seed
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.set_seed" signature="set_seed(seed)">
|
||
Set seed. :param seed: seed :type seed: int
|
||
</Function>
|
||
|
||
### train
|
||
|
||
<Function id="qiskit.aqua.components.neural_networks.NumPyDiscriminator.train" signature="train(data, weights, penalty=False, quantum_instance=None, shots=None)">
|
||
Perform one training step w\.r.t to the discriminator’s parameters
|
||
|
||
**Parameters**
|
||
|
||
* **data** (*tuple(numpy.ndarray, numpy.ndarray)*) – real\_batch: array, Training data batch. generated\_batch: array, Generated data batch.
|
||
* **weights** (*tuple*) – real problem, generated problem
|
||
* **penalty** (*bool*) – Depreciated for classical networks.
|
||
* **quantum\_instance** ([*QuantumInstance*](qiskit.aqua.QuantumInstance "qiskit.aqua.QuantumInstance")) – Depreciated for classical networks.
|
||
* **shots** (*int*) – Number of shots for hardware or qasm execution. Ignored for classical networks.
|
||
|
||
**Returns**
|
||
|
||
with Discriminator loss and updated parameters.
|
||
|
||
**Return type**
|
||
|
||
dict
|
||
</Function>
|
||
</Class>
|
||
|