architect.py

# Create CNN Model
class CNNModel(nn.Module):
    def __init__(self):
        super(CNNModel, self).__init__()
        
        # Convolution 1
        self.cnn1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=3, stride=1, padding=0)
        self.relu1 = nn.ReLU()
        
        # Max pool 1
        self.maxpool1 = nn.MaxPool2d(kernel_size=2)
     
        # Convolution 2
        self.cnn2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=0)
        self.relu2 = nn.ReLU()
        
        # Max pool 2
        self.maxpool2 = nn.MaxPool2d(kernel_size=2)
        
        # Fully connected 1
        self.fc1 = nn.Linear(32 * 5 * 5, 10) 
    
    def forward(self, x):
        # Set 1
        out = self.cnn1(x)
        out = self.relu1(out)
        out = self.maxpool1(out)
        
        # Set 2
        out = self.cnn2(out)
        out = self.relu2(out)
        out = self.maxpool2(out)
        
        #Flatten
        out = out.view(out.size(0), -1)

        #Dense
        out = self.fc1(out)
        
        return out

#Definition of hyperparameters
n_iters = 2500
num_epochs = n_iters / (len(train_x) / batch_size)
num_epochs = int(num_epochs)

# Cross Entropy Loss 
error = nn.CrossEntropyLoss()

# SGD Optimizer
learning_rate = 0.001
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)