model.py

import torch
from torch import nn

class TinyVGG(nn.Module):
    """
    Model architecture copying TinyVGG from: 
    https://poloclub.github.io/cnn-explainer/
    https://www.learnpytorch.io/04_pytorch_custom_datasets/#:~:text=class%20TinyVGG(,device)%0Amodel_0
    """
    def __init__(self, input_shape: int, hidden_units: int, output_shape: int) -> None:
        super().__init__()
        self.conv_block_1 = nn.Sequential(
            nn.Conv2d(in_channels=input_shape, 
                      out_channels=hidden_units, 
                      kernel_size=3, # how big is the square that's going over the image?
                      stride=1, # default
                      padding=1), # options = "valid" (no padding) or "same" (output has same shape as input) or int for specific number 
            nn.ReLU(),
            nn.Conv2d(in_channels=hidden_units, 
                      out_channels=hidden_units,
                      kernel_size=3,
                      stride=1,
                      padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2,
                         stride=2) # default stride value is same as kernel_size
        )
        self.conv_block_2 = nn.Sequential(
            nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2)
        )
        self.classifier = nn.Sequential(
            nn.Flatten(),
            # Where did this in_features shape come from? 
            # It's because each layer of our network compresses and changes the shape of our inputs data.
            nn.Linear(in_features=hidden_units*16*16,
                      out_features=output_shape)
        )
    
    def forward(self, x: torch.Tensor):
        return self.classifier(self.conv_block_2(self.conv_block_1(x)))