# gan¶

GAN metrics.

Classes

 DiscriminatorLoss The Discriminator loss value. EncoderLoss Encoder Loss value. EncodingAccuracy Generator and Encoder accuracy performance. GeneratorLoss Generator loss value. InceptionScore Inception Score Metric.
class ashpy.metrics.gan.DiscriminatorLoss(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

The Discriminator loss value.

__init__(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Initialize the Metric.

Parameters
• model_selection_operator (typing.Callable) –

The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

Note

Model selection is done ONLY if an operator is specified here.

• logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

Return type

None

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.gan.GANContext) – An AshPy Context Object that carries all the information the Metric needs.

Return type

None

class ashpy.metrics.gan.EncoderLoss(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Encoder Loss value.

__init__(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Initialize the Metric.

Parameters
• model_selection_operator (typing.Callable) –

The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

Note

Model selection is done ONLY if an operator is specified here.

• logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

Return type

None

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.gan.GANEncoderContext) – An AshPy Context Object that carries all the information the Metric needs.

Return type

None

class ashpy.metrics.gan.EncodingAccuracy(classifier, model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Generator and Encoder accuracy performance.

Measure the Generator and Encoder performance together, by classifying: G(E(x)), y using a pre-trained classified (on the dataset of x).

__init__(classifier, model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Measure the Generator and Encoder performance together.

This is done by classifying: G(E(x)), y using a pre-trained classified (on the dataset of x).

Parameters
• classifier (tf.keras.Model) – Keras Model to use as a Classifier to measure the accuracy. Generally assumed to be the Inception Model.

• model_selection_operator (typing.Callable) –

The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

Note

Model selection is done ONLY if an operator is specified here.

• logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

Return type

None

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.GANEncoderContext) – An AshPy Context Object that carries all the information the Metric needs.

Return type

None

class ashpy.metrics.gan.GeneratorLoss(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Generator loss value.

__init__(model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Initialize the Metric.

Parameters
• model_selection_operator (typing.Callable) –

The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

Note

Model selection is done ONLY if an operator is specified here.

• logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.GANContext) – An AshPy Context Object that carries all the information the Metric needs.

Return type

None

class ashpy.metrics.gan.InceptionScore(inception, model_selection_operator=<built-in function gt>, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Inception Score Metric.

This class is an implementation of the Inception Score technique for evaluating a GAN.

See Improved Techniques for Training GANs 1.

1

Improved Techniques for Training GANs https://arxiv.org/abs/1606.03498

__init__(inception, model_selection_operator=<built-in function gt>, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Initialize the Metric.

Parameters
static get_or_train_inception(dataset, name, num_classes, epochs, fine_tuning=False, loss_fn=<tensorflow.python.keras.losses.SparseCategoricalCrossentropy object>, optimizer=<tensorflow.python.keras.optimizer_v2.adam.Adam object>, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/master/docs/source/log')[source]

Restore or train (and save) the Inception model.

Parameters
• dataset (tf.data.Dataset) – Dataset to re-train Inception Model on.

• name (str) – Name of this new Inception Model, used for saving it.

• num_classes (int) – Number of classes to use for classification.

• epochs (int) – Epochs to train the Inception model for.

• fine_tuning (bool) – Controls wether the model will be fine-tuned or used as is.

• loss_fn (tf.keras.losses.Loss) – Keras Loss for the model.

• optimizer (tf.keras.optimizers.Optimizer) – Keras optimizer for the model.

• logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

Return type

Model

Returns

tf.keras.Model – The Inception Model.

inception_score(images)[source]

Compute the Inception Score.

Parameters

images (list of [numpy.ndarray]) – A list of ndarray of generated images of 299x299 of size.

Return type

Tensor

Returns

tuple of (numpy.ndarray, numpy.ndarray) – Mean and STD.

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.ClassifierContext) – An AshPy Context holding all the information the Metric needs.

Return type

None