Add CNN class for MNIST in cnn.py and import it to main.py

src/cnn.py

@@ -0,0 +1,21 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class CNN(nn.Module):
+    def __init__(self):
+        super(CNN, self).__init__()
+        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1)
+        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
+        self.fc1 = nn.Linear(64*7*7, 128)
+        self.fc2 = nn.Linear(128, 10)
+
+    def forward(self, x):
+        x = F.relu(self.conv1(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.conv2(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = x.view(-1, 64*7*7)
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return F.log_softmax(x, dim=1)

src/main.py

@@ -5,6 +5,7 @@
 from torchvision import datasets, transforms
 from torch.utils.data import DataLoader
 import numpy as np
+from cnn import CNN
 
 # Step 1: Load MNIST Data and Preprocess
 transform = transforms.Compose([
@@ -31,7 +32,7 @@ def forward(self, x):
         return nn.functional.log_softmax(x, dim=1)
 
 # Step 3: Train the Model
-model = Net()
+model = CNN()
 optimizer = optim.SGD(model.parameters(), lr=0.01)
 criterion = nn.NLLLoss()
 
@@ -40,9 +41,10 @@ def forward(self, x):
 for epoch in range(epochs):
     for images, labels in trainloader:
         optimizer.zero_grad()
+        images = images.view(images.shape[0], 1, 28, 28)
         output = model(images)
         loss = criterion(output, labels)
         loss.backward()
         optimizer.step()
 
-torch.save(model.state_dict(), "mnist_model.pth")
+torch.save(model.state_dict(), "mnist_cnn_model.pth")