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

requirements.txt

@@ -6,7 +6,6 @@ certifi==2022.12.7
 charset-normalizer==2.1.1
 click==8.1.7
 dill==0.3.
-distutils
 exceptiongroup==1.1.3
 fastapi==0.104.0
 filelock==3.9.0

src/cnn.py

@@ -0,0 +1,21 @@
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class CNN(nn.Module):
+    def __init__(self):
+        super().__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

@@ -1,37 +1,39 @@
-from PIL import Image
+import numpy as np
 import torch
 import torch.nn as nn
 import torch.optim as optim
-from torchvision import datasets, transforms
 from torch.utils.data import DataLoader
-import numpy as np
+from torchvision import datasets, transforms
+
+from cnn import CNN
 
 # Step 1: Load MNIST Data and Preprocess
-transform = transforms.Compose([
-    transforms.ToTensor(),
-    transforms.Normalize((0.5,), (0.5,))
-])
+transform = transforms.Compose(
+    [transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]
+)
 
-trainset = datasets.MNIST('.', download=True, train=True, transform=transform)
+trainset = datasets.MNIST(".", download=True, train=True, transform=transform)
 trainloader = DataLoader(trainset, batch_size=64, shuffle=True)
 
+
 # Step 2: Define the PyTorch Model
 class Net(nn.Module):
     def __init__(self):
         super().__init__()
         self.fc1 = nn.Linear(28 * 28, 128)
         self.fc2 = nn.Linear(128, 64)
         self.fc3 = nn.Linear(64, 10)
-    
+
     def forward(self, x):
-        x = x.view(-1, 28 * 28)
+        x = x.view(x.size(0), -1)
         x = nn.functional.relu(self.fc1(x))
         x = nn.functional.relu(self.fc2(x))
         x = self.fc3(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()
 
@@ -45,4 +47,4 @@ def forward(self, x):
         loss.backward()
         optimizer.step()
 
-torch.save(model.state_dict(), "mnist_model.pth")
+torch.save(model.state_dict(), "mnist_model.pth")