import torch
import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # First Conv Block
        self.conv1_1 = nn.Conv2d(3, 32, 3, padding=1)
        self.conv1_2 = nn.Conv2d(32, 32, 3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.dropout1 = nn.Dropout(0.2)

        # Second Conv Block
        self.conv2_1 = nn.Conv2d(32, 64, 3, padding=1)
        self.conv2_2 = nn.Conv2d(64, 64, 3, padding=1)
        self.dropout2 = nn.Dropout(0.3)

        # Third Conv Block
        self.conv3_1 = nn.Conv2d(64, 128, 3, padding=1)
        self.conv3_2 = nn.Conv2d(128, 128, 3, padding=1)
        self.dropout3 = nn.Dropout(0.4)

        # Dense Layers
        self.fc1 = nn.Linear(128 * 4 * 4, 128)
        self.dropout4 = nn.Dropout(0.5)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        # Block 1
        x = F.relu(self.conv1_1(x))
        x = F.relu(self.conv1_2(x))
        x = self.pool(x)
        x = self.dropout1(x)

        # Block 2
        x = F.relu(self.conv2_1(x))
        x = F.relu(self.conv2_2(x))
        x = self.pool(x)
        x = self.dropout2(x)

        # Block 3
        x = F.relu(self.conv3_1(x))
        x = F.relu(self.conv3_2(x))
        x = self.pool(x)
        x = self.dropout3(x)

        # Flatten
        x = x.view(-1, 128 * 4 * 4)
        
        # Dense
        x = F.relu(self.fc1(x))
        x = self.dropout4(x)
        x = self.fc2(x)
        return x

def create_model():
    return Net()