Merge branch 'main' into svekars-patch-9

Author: Svetlana Karslioglu

Makefile

@@ -82,7 +82,7 @@ download:
 	tar $(TAROPTS) -xzf $(DATADIR)/UrbanSound8K.tar.gz -C ./beginner_source/data/
 
 	# Download model for beginner_source/fgsm_tutorial.py
-	wget -nv -N https://s3.amazonaws.com/pytorch-tutorial-assets/lenet_mnist_model.pth -P $(DATADIR)
+	wget -nv -N 'https://docs.google.com/uc?export=download&id=1HJV2nUHJqclXQ8flKvcWmjZ-OU5DGatl' -O $(DATADIR)/lenet_mnist_model.pth
 	cp $(DATADIR)/lenet_mnist_model.pth ./beginner_source/data/lenet_mnist_model.pth
 
 	# Download model for advanced_source/dynamic_quantization_tutorial.py

advanced_source/neural_style_tutorial.py

@@ -14,7 +14,7 @@
 developed by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge.
 Neural-Style, or Neural-Transfer, allows you to take an image and
 reproduce it with a new artistic style. The algorithm takes three images,
-an input image, a content-image, and a style-image, and changes the input 
+an input image, a content-image, and a style-image, and changes the input
 to resemble the content of the content-image and the artistic style of the style-image.
 
  
@@ -70,6 +70,7 @@
 # method is used to move tensors or modules to a desired device. 
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+torch.set_default_device(device)
 
 ######################################################################
 # Loading the Images
@@ -261,7 +262,7 @@ def forward(self, input):
 # network to evaluation mode using ``.eval()``.
 # 
 
-cnn = models.vgg19(pretrained=True).features.to(device).eval()
+cnn = models.vgg19(pretrained=True).features.eval()
 
 
 
@@ -271,8 +272,8 @@ def forward(self, input):
 # We will use them to normalize the image before sending it into the network.
 # 
 
-cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
-cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device)
+cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406])
+cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225])
 
 # create a module to normalize input image so we can easily put it in a
 # ``nn.Sequential``
@@ -308,7 +309,7 @@ def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
                                content_layers=content_layers_default,
                                style_layers=style_layers_default):
     # normalization module
-    normalization = Normalization(normalization_mean, normalization_std).to(device)
+    normalization = Normalization(normalization_mean, normalization_std)
 
     # just in order to have an iterable access to or list of content/style
     # losses
@@ -373,7 +374,7 @@ def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
 #
 # ::
 #
-#    input_img = torch.randn(content_img.data.size(), device=device)
+#    input_img = torch.randn(content_img.data.size())
 
 # add the original input image to the figure:
 plt.figure()

beginner_source/examples_autograd/polynomial_autograd.py

@@ -18,23 +18,23 @@
 import math
 
 dtype = torch.float
-device = torch.device("cpu")
-# device = torch.device("cuda:0")  # Uncomment this to run on GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+torch.set_default_device(device)
 
 # Create Tensors to hold input and outputs.
 # By default, requires_grad=False, which indicates that we do not need to
 # compute gradients with respect to these Tensors during the backward pass.
-x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
+x = torch.linspace(-math.pi, math.pi, 2000, dtype=dtype)
 y = torch.sin(x)
 
 # Create random Tensors for weights. For a third order polynomial, we need
 # 4 weights: y = a + b x + c x^2 + d x^3
 # Setting requires_grad=True indicates that we want to compute gradients with
 # respect to these Tensors during the backward pass.
-a = torch.randn((), device=device, dtype=dtype, requires_grad=True)
-b = torch.randn((), device=device, dtype=dtype, requires_grad=True)
-c = torch.randn((), device=device, dtype=dtype, requires_grad=True)
-d = torch.randn((), device=device, dtype=dtype, requires_grad=True)
+a = torch.randn((), dtype=dtype, requires_grad=True)
+b = torch.randn((), dtype=dtype, requires_grad=True)
+c = torch.randn((), dtype=dtype, requires_grad=True)
+d = torch.randn((), dtype=dtype, requires_grad=True)
 
 learning_rate = 1e-6
 for t in range(2000):

beginner_source/fgsm_tutorial.py

@@ -123,7 +123,7 @@
 # -  ``pretrained_model`` - path to the pretrained MNIST model which was
 #    trained with
 #    `pytorch/examples/mnist <https://github.com/pytorch/examples/tree/master/mnist>`__.
-#    For simplicity, download the pretrained model `here <https://drive.google.com/drive/folders/1fn83DF14tWmit0RTKWRhPq5uVXt73e0h?usp=sharing>`__.
+#    For simplicity, download the pretrained model `here <https://drive.google.com/file/d/1HJV2nUHJqclXQ8flKvcWmjZ-OU5DGatl/view?usp=drive_link>`__.
 # 
 # -  ``use_cuda`` - boolean flag to use CUDA if desired and available.
 #    Note, a GPU with CUDA is not critical for this tutorial as a CPU will
@@ -154,26 +154,34 @@
 class Net(nn.Module):
     def __init__(self):
         super(Net, self).__init__()
-        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
-        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
-        self.conv2_drop = nn.Dropout2d()
-        self.fc1 = nn.Linear(320, 50)
-        self.fc2 = nn.Linear(50, 10)
+        self.conv1 = nn.Conv2d(1, 32, 3, 1)
+        self.conv2 = nn.Conv2d(32, 64, 3, 1)
+        self.dropout1 = nn.Dropout(0.25)
+        self.dropout2 = nn.Dropout(0.5)
+        self.fc1 = nn.Linear(9216, 128)
+        self.fc2 = nn.Linear(128, 10)
 
     def forward(self, x):
-        x = F.relu(F.max_pool2d(self.conv1(x), 2))
-        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
-        x = x.view(-1, 320)
-        x = F.relu(self.fc1(x))
-        x = F.dropout(x, training=self.training)
+        x = self.conv1(x)
+        x = F.relu(x)
+        x = self.conv2(x)
+        x = F.relu(x)
+        x = F.max_pool2d(x, 2)
+        x = self.dropout1(x)
+        x = torch.flatten(x, 1)
+        x = self.fc1(x)
+        x = F.relu(x)
+        x = self.dropout2(x)
         x = self.fc2(x)
-        return F.log_softmax(x, dim=1)
+        output = F.log_softmax(x, dim=1)
+        return output
 
 # MNIST Test dataset and dataloader declaration
 test_loader = torch.utils.data.DataLoader(
     datasets.MNIST('../data', train=False, download=True, transform=transforms.Compose([
             transforms.ToTensor(),
-            ])),
+            transforms.Normalize((0.1307,), (0.3081,)),
+            ])), 
         batch_size=1, shuffle=True)
 
 # Define what device we are using
@@ -184,7 +192,7 @@ def forward(self, x):
 model = Net().to(device)
 
 # Load the pretrained model
-model.load_state_dict(torch.load(pretrained_model, weights_only=True, map_location='cpu'))
+model.load_state_dict(torch.load(pretrained_model, map_location=device))
 
 # Set the model in evaluation mode. In this case this is for the Dropout layers
 model.eval()
@@ -219,6 +227,26 @@ def fgsm_attack(image, epsilon, data_grad):
     # Return the perturbed image
     return perturbed_image
 
+# restores the tensors to their original scale
+def denorm(batch, mean=[0.1307], std=[0.3081]):
+    """
+    Convert a batch of tensors to their original scale.
+
+    Args:
+        batch (torch.Tensor): Batch of normalized tensors.
+        mean (torch.Tensor or list): Mean used for normalization.
+        std (torch.Tensor or list): Standard deviation used for normalization.
+
+    Returns:
+        torch.Tensor: batch of tensors without normalization applied to them.
+    """
+    if isinstance(mean, list):
+        mean = torch.tensor(mean).to(device)
+    if isinstance(std, list):
+        std = torch.tensor(std).to(device)
+    
+    return batch * std.view(1, -1, 1, 1) + mean.view(1, -1, 1, 1)
+
 
 ######################################################################
 # Testing Function
@@ -273,11 +301,17 @@ def test( model, device, test_loader, epsilon ):
         # Collect ``datagrad``
         data_grad = data.grad.data
 
+        # Restore the data to its original scale
+        data_denorm = denorm(data)
+
         # Call FGSM Attack
-        perturbed_data = fgsm_attack(data, epsilon, data_grad)
+        perturbed_data = fgsm_attack(data_denorm, epsilon, data_grad)
+
+        # Reapply normalization
+        perturbed_data_normalized = transforms.Normalize((0.1307,), (0.3081,))(perturbed_data)
 
         # Re-classify the perturbed image
-        output = model(perturbed_data)
+        output = model(perturbed_data_normalized)
 
         # Check for success
         final_pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability