art.estimators
¶
Base Class Estimator¶

class
art.estimators.
BaseEstimator
(model=None, clip_values: Optional[CLIP_VALUES_TYPE] = None, preprocessing_defences: Optional[Union[Preprocessor, List[Preprocessor]]] = None, postprocessing_defences: Optional[Union[Postprocessor, List[Postprocessor]]] = None, preprocessing: PREPROCESSING_TYPE = (0, 1))¶ The abstract base class BaseEstimator defines the basic requirements of an estimator in ART. The BaseEstimator is is the highest abstraction of a machine learning model in ART.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

abstract
fit
(x, y, **kwargs) → None¶ Fit the estimator using the training data (x, y).
 Parameters
x (Format as expected by the model) – Training data.
y (Format as expected by the model) – Target values.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
model
¶ Return the model.
 Returns
The model.

abstract
predict
(x, **kwargs) → Any¶ Perform prediction of the estimator for input x.
 Parameters
x (Format as expected by the model) – Samples.
 Returns
Predictions by the model.
 Return type
Format as produced by the model

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

property
Mixin Base Class Loss Gradients¶

class
art.estimators.
LossGradientsMixin
¶ Mixin abstract base class defining additional functionality for estimators providing loss gradients. An estimator of this type can be combined with whitebox attacks. This mixin abstract base class has to be mixed in with class BaseEstimator.

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

abstract
Mixin Base Class Neural Networks¶

class
art.estimators.
NeuralNetworkMixin
(**kwargs)¶ Mixin abstract base class defining additional functionality required for neural network estimators. This base class has to be mixed in with class BaseEstimator.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

abstract
fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

abstract
loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

property
Mixin Base Class Decision Trees¶

class
art.estimators.
DecisionTreeMixin
¶ Mixin abstract base class defining additional functionality for decisiontreebased estimators. This mixin abstract base class has to be mixed in with class BaseEstimator.

abstract
get_trees
() → List[Tree]¶ Get the decision trees.
 Returns
A list of decision trees.

abstract
Base Class KerasEstimator¶

class
art.estimators.
KerasEstimator
(**kwargs)¶ Estimator class for Keras models.

__init__
(**kwargs) → None¶ Estimator class for Keras models.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

property
model
¶ Return the model.
 Returns
The model.

predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

Base Class MXEstimator¶

class
art.estimators.
MXEstimator
(**kwargs)¶ Estimator for MXNet Gluon models.

__init__
(**kwargs) → None¶ Estimator class for MXNet Gluon models.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

property
model
¶ Return the model.
 Returns
The model.

predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

Base Class PyTorchEstimator¶

class
art.estimators.
PyTorchEstimator
(device_type: str = 'gpu', **kwargs)¶ Estimator class for PyTorch models.

__init__
(device_type: str = 'gpu', **kwargs) → None¶ Estimator class for PyTorch models.
 Parameters
channels_first – Set channels first or last.
clip_values – Tuple of the form (min, max) of floats or np.ndarray representing the minimum and maximum values allowed for features. If floats are provided, these will be used as the range of all features. If arrays are provided, each value will be considered the bound for a feature, thus the shape of clip values needs to match the total number of features.
preprocessing_defences – Preprocessing defence(s) to be applied by the classifier.
postprocessing_defences – Postprocessing defence(s) to be applied by the classifier.
preprocessing – Tuple of the form (subtrahend, divisor) of floats or np.ndarray of values to be used for data preprocessing. The first value will be subtracted from the input. The input will then be divided by the second one.
device_type (
str
) – Type of device on which the classifier is run, either gpu or cpu.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

property
model
¶ Return the model.
 Returns
The model.

predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

Base Class ScikitlearnEstimator¶

class
art.estimators.
ScikitlearnEstimator
(model=None, clip_values: Optional[CLIP_VALUES_TYPE] = None, preprocessing_defences: Optional[Union[Preprocessor, List[Preprocessor]]] = None, postprocessing_defences: Optional[Union[Postprocessor, List[Postprocessor]]] = None, preprocessing: PREPROCESSING_TYPE = (0, 1))¶ Estimator class for scikitlearn models.

__init__
(model=None, clip_values: Optional[CLIP_VALUES_TYPE] = None, preprocessing_defences: Optional[Union[Preprocessor, List[Preprocessor]]] = None, postprocessing_defences: Optional[Union[Postprocessor, List[Postprocessor]]] = None, preprocessing: PREPROCESSING_TYPE = (0, 1))¶ Initialize a BaseEstimator object.
 Parameters
model – The model
clip_values – Tuple of the form (min, max) of floats or np.ndarray representing the minimum and maximum values allowed for features. If floats are provided, these will be used as the range of all features. If arrays are provided, each value will be considered the bound for a feature, thus the shape of clip values needs to match the total number of features.
preprocessing_defences – Preprocessing defence(s) to be applied by the estimator.
postprocessing_defences – Postprocessing defence(s) to be applied by the estimator.
preprocessing – Tuple of the form (subtrahend, divisor) of floats or np.ndarray of values to be used for data preprocessing. The first value will be subtracted from the input and the results will be divided by the second value.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

abstract
fit
(x, y, **kwargs) → None¶ Fit the estimator using the training data (x, y).
 Parameters
x (Format as expected by the model) – Training data.
y (Format as expected by the model) – Target values.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
model
¶ Return the model.
 Returns
The model.

abstract
predict
(x, **kwargs) → Any¶ Perform prediction of the estimator for input x.
 Parameters
x (Format as expected by the model) – Samples.
 Returns
Predictions by the model.
 Return type
Format as produced by the model

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

Base Class TensorFlowEstimator¶

class
art.estimators.
TensorFlowEstimator
(**kwargs)¶ Estimator class for TensorFlow models.

__init__
(**kwargs) → None¶ Estimator class for TensorFlow models.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

property
model
¶ Return the model.
 Returns
The model.

predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

property
sess
¶ Get current TensorFlow session.
 Returns
The current TensorFlow session.

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.

Base Class TensorFlowV2Estimator¶

class
art.estimators.
TensorFlowV2Estimator
(**kwargs)¶ Estimator class for TensorFlow v2 models.

__init__
(**kwargs)¶ Estimator class for TensorFlow v2 models.

property
channel_index
¶  Returns
Index of the axis containing the color channels in the samples x.

property
channels_first
¶  Returns
Boolean to indicate index of the color channels in the sample x.

property
clip_values
¶ Return the clip values of the input samples.
 Returns
Clip values (min, max).

fit
(x: numpy.ndarray, y, batch_size: int = 128, nb_epochs: int = 20, **kwargs) → None¶ Fit the model of the estimator on the training data x and y.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (Format as expected by the model) – Target values.
batch_size (
int
) – Batch size.nb_epochs (
int
) – Number of training epochs.

fit_generator
(generator: DataGenerator, nb_epochs: int = 20, **kwargs) → None¶ Fit the estimator using a generator yielding training batches. Implementations can provide frameworkspecific versions of this function to speedup computation.
 Parameters
generator – Batch generator providing (x, y) for each epoch.
nb_epochs (
int
) – Number of training epochs.

abstract
get_activations
(x: numpy.ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) → numpy.ndarray¶ Return the output of a specific layer for samples x where layer is the index of the layer between 0 and nb_layers  1 or the name of the layer. The number of layers can be determined by counting the results returned by calling `layer_names.
 Return type
ndarray
 Parameters
x (
ndarray
) – Sampleslayer – Index or name of the layer.
batch_size (
int
) – Batch size.framework (
bool
) – If true, return the intermediate tensor representation of the activation.
 Returns
The output of layer, where the first dimension is the batch size corresponding to x.

get_params
() → Dict[str, Any]¶ Get all parameters and their values of this estimator.
 Returns
A dictionary of string parameter names to their value.

property
input_shape
¶ Return the shape of one input sample.
 Returns
Shape of one input sample.

property
layer_names
¶ Return the names of the hidden layers in the model, if applicable.
 Returns
The names of the hidden layers in the model, input and output layers are ignored.
Warning
layer_names tries to infer the internal structure of the model. This feature comes with no guarantees on the correctness of the result. The intended order of the layers tries to match their order in the model, but this is not guaranteed either.

property
learning_phase
¶ The learning phase set by the user. Possible values are True for training or False for prediction and None if it has not been set by the library. In the latter case, the library does not do any explicit learning phase manipulation and the current value of the backend framework is used. If a value has been set by the user for this property, it will impact all following computations for model fitting, prediction and gradients.
 Returns
Learning phase.

loss
(x: numpy.ndarray, y: numpy.ndarray, **kwargs) → numpy.ndarray¶ Compute the loss of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).y (
ndarray
) – Target values (class labels) onehotencoded of shape (nb_samples, nb_classes) or indices of shape (nb_samples,).
 Returns
Loss values.
 Return type
Format as expected by the model

abstract
loss_gradient
(x, y, **kwargs)¶ Compute the gradient of the loss function w.r.t. x.
 Parameters
x (Format as expected by the model) – Samples.
y (Format as expected by the model) – Target values.
 Returns
Loss gradients w.r.t. x in the same format as x.
 Return type
Format as expected by the model

property
model
¶ Return the model.
 Returns
The model.

predict
(x: numpy.ndarray, batch_size: int = 128, **kwargs)¶ Perform prediction of the neural network for samples x.
 Parameters
x (
ndarray
) – Samples of shape (nb_samples, nb_features) or (nb_samples, nb_pixels_1, nb_pixels_2, nb_channels) or (nb_samples, nb_channels, nb_pixels_1, nb_pixels_2).batch_size (
int
) – Batch size.
 Returns
Predictions.
 Return type
Format as expected by the model

abstract
set_learning_phase
(train: bool) → None¶ Set the learning phase for the backend framework.
 Parameters
train (
bool
) – True if the learning phase is training, otherwise False.

set_params
(**kwargs) → None¶ Take a dictionary of parameters and apply checks before setting them as attributes.
 Parameters
kwargs – A dictionary of attributes.
