model.py

import torch
from torch import nn


class MiniVisionV3(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            nn.Conv2d(1, 32, 3, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(2),

            nn.Conv2d(32, 64, 3, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(2),

            nn.Conv2d(64, 128, 3, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(2),

            nn.Flatten(),
            nn.Linear(1152, 256),
            nn.ReLU(),
            nn.Dropout(0.3),
            nn.Linear(256, 47),
        )

    def forward(self, x):
        x = self.model(x)
        return x

if __name__ == '__main__':
    minivisionv3 = MiniVisionV3()

    total_params = sum(param.numel() for param in minivisionv3.parameters())
    print(f"Total params: {total_params / 1000000: .2f}M")

    # with torch.no_grad():
    #     input = torch.randn(256, 1, 28, 28)
    #     output = minivisionv3(input)
    #     print(output)