devanshuDesai · September 10, 2024 16:23 · Dec 1, 2019 · Nov 9, 2019 · Nov 9, 2019 · Nov 9, 2019
diff --git a/mnist_dodgers.py b/mnist_dodgers.py
@@ -1,5 +1,6 @@
 import torch
 from torch import nn
+from tqdm import tqdm_notebook
 
 class CNN(nn.Module):
     def __init__(self, input_size, num_classes):

diff --git a/mnist_dodgers.py b/mnist_dodgers.py
@@ -1,3 +1,6 @@
+import torch
+from torch import nn
+
 class CNN(nn.Module):
     def __init__(self, input_size, num_classes):
         """
@@ -7,7 +10,7 @@ def __init__(self, input_size, num_classes):
             num_classes: 10
         """
         super(CNN, self).__init__()
-        ### YOUR CODE HERE
+
         self.layer1 = nn.Sequential(
             nn.Conv2d(input_size[0], 32, kernel_size=5),
             nn.ReLU(),
@@ -19,7 +22,6 @@ def __init__(self, input_size, num_classes):
             nn.MaxPool2d(kernel_size=2))
 
         self.fc1 = nn.Linear(4 * 4 * 64, num_classes)
-        ### END OF CODE
 
 
     def forward(self, x):
@@ -28,10 +30,42 @@ def forward(self, x):
         Args:
             x: (Nx1x28x28) tensor
         """
-        ### YOUR CODE HERE
         x = self.layer1(x)
         x = self.layer2(x)
         x = x.reshape(x.size(0), -1)
         x = self.fc1(x)
-        ### END OF CODE
-        return x
+        return x
+
+    model = CNN((1, 28, 28), 10)
+
+opts = {
+    'lr': 1e-3,
+    'epochs': 20,
+    'batch_size': 64
+}
+
+optimizer = torch.optim.Adam(model.parameters(), opts['lr'])
+criterion = torch.nn.CrossEntropyLoss()  # loss function
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=opts['batch_size'], shuffle=True)
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=opts['batch_size'], shuffle=True)
+
+for epoch in range(opts['epochs']):
+    train_loss = []
+    for i, (data, labels) in tqdm_notebook(enumerate(train_loader), total=len(train_loader)):
+        # pass data through network
+        outputs = model(data)
+        loss = criterion(outputs, labels)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+        train_loss.append(loss.item())
+    test_loss = []
+    test_accuracy = []
+    for i, (data, labels) in enumerate(test_loader):
+        # pass data through network
+        outputs = model(data)
+        _, predicted = torch.max(outputs.data, 1)
+        loss = criterion(outputs, labels)
+        test_loss.append(loss.item())
+        test_accuracy.append((predicted == labels).sum().item() / predicted.size(0))
+    print('epoch: {}, train loss: {}, test loss: {}, test accuracy: {}'.format(epoch, np.mean(train_loss), np.mean(test_loss), np.mean(test_accuracy)))
diff --git a/mnist_dodgers.py b/mnist_dodgers.py
@@ -0,0 +1,37 @@
+class CNN(nn.Module):
+    def __init__(self, input_size, num_classes):
+        """
+        init convolution and activation layers
+        Args:
+            input_size: (1,28,28)
+            num_classes: 10
+        """
+        super(CNN, self).__init__()
+        ### YOUR CODE HERE
+        self.layer1 = nn.Sequential(
+            nn.Conv2d(input_size[0], 32, kernel_size=5),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2))
+
+        self.layer2 = nn.Sequential(
+            nn.Conv2d(32, 64, kernel_size=5),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2))
+
+        self.fc1 = nn.Linear(4 * 4 * 64, num_classes)
+        ### END OF CODE
+
+
+    def forward(self, x):
+        """
+        forward function describes how input tensor is transformed to output tensor
+        Args:
+            x: (Nx1x28x28) tensor
+        """
+        ### YOUR CODE HERE
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = x.reshape(x.size(0), -1)
+        x = self.fc1(x)
+        ### END OF CODE
+        return x
No results found