cnn.py

from torch import nn
from torchsummary import summary


class CNNNetwork(nn.Module):

    def __init__(self):
        super().__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=64,
                kernel_size=5,
                stride=1
            ),
            nn.ReLU(),
        )

        self.conv2 = nn.Sequential(
            nn.Conv2d(
                in_channels=64,
                out_channels=128,
                kernel_size=5,
                stride=1
            ),
            nn.ReLU(),
        )
        
        self.conv3 = nn.Sequential(
            nn.Conv2d(
                in_channels=128,
                out_channels=256,
                kernel_size=5,
                stride=1
            ),
            nn.ReLU(),
        )
        

        self.flatten = nn.Flatten()
        self.pool = nn.AdaptiveAvgPool2d((1, 1))
        self.classifier = nn.Sequential(
                nn.Linear(256, 256),
                nn.ReLU(),
                nn.Linear(256, 10)
        )    

    def forward(self, input_data):
        x = self.conv1(input_data)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.pool(x)        
        x = self.flatten(x)
        logits = self.classifier(x)
        return logits

if __name__ == "__main__":
    cnn = CNNNetwork()
    summary(cnn.cuda(), (1, 64, 44))