Fixing compatibility issue between PyTorch YOLO and AdversarialPatchPyTorch, updating notebook

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

Author: kieranfraser

art/attacks/evasion/adversarial_patch/adversarial_patch_pytorch.py

@@ -573,9 +573,9 @@ def __getitem__(self, idx):
                     img = torch.from_numpy(self.x[idx])
 
                     target = {}
-                    target["boxes"] = torch.from_numpy(y[idx]["boxes"])
-                    target["labels"] = torch.from_numpy(y[idx]["labels"])
-                    target["scores"] = torch.from_numpy(y[idx]["scores"])
+                    target["boxes"] = torch.from_numpy(self.y[idx]["boxes"])
+                    target["labels"] = torch.from_numpy(self.y[idx]["labels"])
+                    target["scores"] = torch.from_numpy(self.y[idx]["scores"])
                     mask_i = torch.from_numpy(self.mask[idx])
 
                     return img, target, mask_i
@@ -600,19 +600,21 @@ def __getitem__(self, idx):
                     if isinstance(target, torch.Tensor):
                         target = target.to(self.estimator.device)
                     else:
-                        target["boxes"] = target["boxes"].to(self.estimator.device)
-                        target["labels"] = target["labels"].to(self.estimator.device)
-                        target["scores"] = target["scores"].to(self.estimator.device)
+                        target["boxes"] = target["boxes"][0].to(self.estimator.device)
+                        target["labels"] = target["labels"][0].to(self.estimator.device)
+                        target["scores"] = target["scores"][0].to(self.estimator.device)
+                        target = [target]
                     _ = self._train_step(images=images, target=target, mask=None)
             else:
                 for images, target, mask_i in data_loader:
                     images = images.to(self.estimator.device)
                     if isinstance(target, torch.Tensor):
                         target = target.to(self.estimator.device)
                     else:
-                        target["boxes"] = target["boxes"].to(self.estimator.device)
-                        target["labels"] = target["labels"].to(self.estimator.device)
-                        target["scores"] = target["scores"].to(self.estimator.device)
+                        target["boxes"] = target["boxes"][0].to(self.estimator.device)
+                        target["labels"] = target["labels"][0].to(self.estimator.device)
+                        target["scores"] = target["scores"][0].to(self.estimator.device)
+                        target = [target]
                     mask_i = mask_i.to(self.estimator.device)
                     _ = self._train_step(images=images, target=target, mask=mask_i)
 

art/estimators/object_detection/pytorch_yolo.py

@@ -321,7 +321,10 @@ def _preprocess_and_convert_inputs(
 
             # Set gradients
             if not no_grad:
-                x_tensor.requires_grad = True
+                if x_tensor.is_leaf:
+                    x_tensor.requires_grad = True
+                else:
+                    x_tensor.retain_grad()
 
             # Apply framework-specific preprocessing
             x_preprocessed, y_preprocessed = self._apply_preprocessing(x=x_tensor, y=y_tensor, fit=fit, no_grad=no_grad)
@@ -375,6 +378,8 @@ 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)