Removing fix for spurious YOLO predictions as generates nans due to alpha in python yolo libraries. Adding test for adversarial patch

Signed-off-by: Kieran Fraser <[email protected]>

Author: kieranfraser

art/estimators/object_detection/pytorch_yolo.py

@@ -378,8 +378,6 @@ def _get_losses(
         :return: Loss gradients of the same shape as `x`.
         """
         self._model.train()
-        self.set_batchnorm(train=False)
-        self.set_dropout(train=False)
 
         # Apply preprocessing and convert to tensors
         x_preprocessed, y_preprocessed = self._preprocess_and_convert_inputs(x=x, y=y, fit=False, no_grad=False)

tests/estimators/object_detection/test_pytorch_yolo.py

@@ -367,7 +367,7 @@ def test_compute_loss(art_warning, get_pytorch_yolo):
         # Compute loss
         loss = object_detector.compute_loss(x=x_test, y=y_test)
 
-        assert pytest.approx(11.20741, abs=0.9) == float(loss)
+        assert pytest.approx(11.20741, abs=1.5) == float(loss)
 
     except ARTTestException as e:
         art_warning(e)
@@ -386,3 +386,52 @@ def test_pgd(art_warning, get_pytorch_yolo):
 
     except ARTTestException as e:
         art_warning(e)
+
+@pytest.mark.only_with_platform("pytorch")
+def test_patch(art_warning, get_pytorch_yolo):
+    try:
+        
+        from art.attacks.evasion import AdversarialPatchPyTorch
+
+        rotation_max=0.0
+        scale_min=0.1
+        scale_max=0.3
+        distortion_scale_max=0.0
+        learning_rate=1.99
+        max_iter=2
+        batch_size=16
+        patch_shape=(3, 5, 5)
+        patch_type="circle"
+        optimizer="pgd"
+
+        object_detector, x_test, y_test = get_pytorch_yolo
+
+        ap = AdversarialPatchPyTorch(estimator=object_detector, rotation_max=rotation_max, 
+                      scale_min=scale_min, scale_max=scale_max, optimizer=optimizer, distortion_scale_max=distortion_scale_max,
+                      learning_rate=learning_rate, max_iter=max_iter, batch_size=batch_size,
+                      patch_shape=patch_shape, patch_type=patch_type, verbose=True, targeted=False)
+
+        _, _ = ap.generate(x=x_test, y=y_test)
+
+        patched_images = ap.apply_patch(x_test, scale=0.4)
+        result = object_detector.predict(patched_images)
+
+        assert result[0]["scores"].shape == (10647,)
+        expected_detection_scores = np.asarray(
+            [
+                4.3653536e-08,
+                3.3987994e-06,
+                2.5681820e-06,
+                3.9782722e-06,
+                2.1766680e-05,
+                2.6138965e-05,
+                6.3377396e-05,
+                7.6248516e-06,
+                4.3447722e-06,
+                3.6515078e-06,
+            ]
+        )
+        np.testing.assert_raises(AssertionError, np.testing.assert_array_almost_equal, result[0]["scores"][:10], expected_detection_scores, 6)
+
+    except ARTTestException as e:
+        art_warning(e)