art.experimental.estimators

Experimental Estimator API

Base Class JaxEstimator

class art.experimental.estimators.JaxEstimator(**kwargs)

Estimator class for Jax models.

__init__(**kwargs) None

Estimator class for Jax 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 – Type of device on which the classifier is run, either gpu or cpu.

property channels_first: bool
Returns

Boolean to indicate index of the color channels in the sample x.

property clip_values: Optional[CLIP_VALUES_TYPE]

Return the clip values of the input samples.

Returns

Clip values (min, max).

compute_loss(x: ndarray, y: Any, **kwargs) ndarray

Compute the loss of the estimator for samples x.

Parameters
  • x (ndarray) – Input samples.

  • y – Target values.

Returns

Loss values.

Return type

Format as expected by the model

compute_loss_from_predictions(pred: ndarray, y: ndarray, **kwargs) ndarray

Compute the loss of the estimator for predictions pred.

Return type

ndarray

Parameters
  • pred (ndarray) – Model predictions.

  • y (ndarray) – Target values.

Returns

Loss values.

fit(x: 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 framework-specific versions of this function to speed-up computation.

Parameters
  • generator – Batch generator providing (x, y) for each epoch.

  • nb_epochs (int) – Number of training epochs.

abstract get_activations(x: ndarray, layer: Union[int, str], batch_size: int, framework: bool = False) 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) – Samples

  • layer – 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.

abstract property input_shape: Tuple[int, ...]

Return the shape of one input sample.

Returns

Shape of one input sample.

property layer_names: Optional[List[str]]

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.

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: 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

set_params(**kwargs) None

Take a dictionary of parameters and apply checks before setting them as attributes.

Parameters

kwargs – A dictionary of attributes.