Fix LGTM alerts

Signed-off-by: Beat Buesser <[email protected]>

Author: Beat Buesser

art/estimators/certification/randomized_smoothing/numpy.py

@@ -22,13 +22,14 @@
 """
 from __future__ import absolute_import, division, print_function, unicode_literals
 
+import logging
+from typing import List, Union, TYPE_CHECKING, Tuple
+
 import numpy as np
 
-from art.estimators.estimator import BaseEstimator
+from art.estimators.estimator import BaseEstimator, LossGradientsMixin, NeuralNetworkMixin
 from art.estimators.certification.randomized_smoothing.randomized_smoothing import RandomizedSmoothingMixin
 from art.estimators.classification import ClassifierMixin, ClassGradientsMixin
-import logging
-from typing import List, Union, TYPE_CHECKING, Tuple
 
 if TYPE_CHECKING:
     from art.utils import CLASSIFIER_LOSS_GRADIENTS_TYPE
@@ -37,7 +38,12 @@
 
 
 class NumpyRandomizedSmoothing(
-    RandomizedSmoothingMixin, ClassGradientsMixin, ClassifierMixin, BaseEstimator
+    RandomizedSmoothingMixin,
+    ClassGradientsMixin,
+    ClassifierMixin,
+    NeuralNetworkMixin,
+    LossGradientsMixin,
+    BaseEstimator,
 ):
     """
     Implementation of Randomized Smoothing applied to classifier predictions and gradients, as introduced
@@ -111,6 +117,7 @@ def loss_gradient(self, x: np.ndarray, y: np.ndarray, **kwargs) -> np.ndarray:
     def class_gradient(self, x: np.ndarray, label: Union[int, List[int]] = None, **kwargs) -> np.ndarray:
         """
         Compute per-class derivatives of the given classifier w.r.t. `x` of original classifier.
+        :param x: Sample input with shape as expected by the model.
         :param label: Index of a specific per-class derivative. If an integer is provided, the gradient of that class
                       output is computed for all samples. If multiple values as provided, the first dimension should
                       match the batch size of `x`, and each value will be used as target for its corresponding sample in

art/estimators/certification/randomized_smoothing/pytorch.py

@@ -218,14 +218,18 @@ def class_gradient(self, x: np.ndarray, label: Union[int, List[int], None] = Non
         """
         raise NotImplementedError
 
-    def loss(self, x: np.ndarray, y: np.ndarray, **kwargs) -> np.ndarray:
+    def loss(self, x: np.ndarray, y: np.ndarray, reduction: str = "none", **kwargs) -> np.ndarray:
         """
         Compute the loss of the neural network for samples `x`.
 
         :param x: 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).
         :param y: Target values (class labels) one-hot-encoded of shape `(nb_samples, nb_classes)` or indices
                   of shape `(nb_samples,)`.
+        :param reduction: Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'.
+                   'none': no reduction will be applied
+                   'mean': the sum of the output will be divided by the number of elements in the output,
+                   'sum': the output will be summed.
         :return: Loss values.
         :rtype: Format as expected by the `model`
         """

art/estimators/certification/randomized_smoothing/randomized_smoothing.py

@@ -67,7 +67,6 @@ def _predict_classifier(self, x: np.ndarray, batch_size: int) -> np.ndarray:
         """
         raise NotImplementedError
 
-    # pylint: disable=W0221
     def predict(self, x: np.ndarray, batch_size: int = 128, **kwargs) -> np.ndarray:
         """
         Perform prediction of the given classifier for a batch of inputs, taking an expectation over transformations.

art/estimators/certification/randomized_smoothing/tensorflow.py

@@ -221,14 +221,18 @@ def class_gradient(self, x: np.ndarray, label: Union[int, List[int], None] = Non
         """
         raise NotImplementedError
 
-    def loss(self, x: np.ndarray, y: np.ndarray, **kwargs) -> np.ndarray:
+    def loss(self, x: np.ndarray, y: np.ndarray, reduction: str = "none", **kwargs) -> np.ndarray:
         """
         Compute the loss of the neural network for samples `x`.
 
         :param x: 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).
         :param y: Target values (class labels) one-hot-encoded of shape `(nb_samples, nb_classes)` or indices
                   of shape `(nb_samples,)`.
+        :param reduction: Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'.
+                   'none': no reduction will be applied
+                   'mean': the sum of the output will be divided by the number of elements in the output,
+                   'sum': the output will be summed.
         :return: Loss values.
         :rtype: Format as expected by the `model`
         """