# -*- coding: utf-8 -*-
"""mnist_torch_dec25.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1IxH-hIFwyEUPOjFB6MltbKAZzPHUwoxk

#CNN for MNIST classification (Pytorch)

(c) G. Turinici 2025

#NN definition : class etc
"""

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
from tqdm import tqdm

# --- Data ---
transform = transforms.ToTensor()
train = datasets.MNIST(root='.', train=True, download=True, transform=transform)
test  = datasets.MNIST(root='.', train=False, download=True, transform=transform)

train_loader = DataLoader(train, batch_size=64, shuffle=True)
test_loader  = DataLoader(test,  batch_size=1000)

# --- Model ---
class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 32, 3, padding=1), nn.ReLU(),
            nn.Conv2d(32, 64, 3, padding=1), nn.ReLU(),
            nn.MaxPool2d(2)
        )
        self.fc = nn.Linear(64*14*14, 10)

    def forward(self, x):
        x = self.conv(x)
        x = x.view(x.size(0), -1)
        return self.fc(x)

"""#Instantiation of the model"""

model = CNN()
opt = optim.Adam(model.parameters())
loss_fn = nn.CrossEntropyLoss()

"""#Train"""

# --- Train ---
for epoch in range(1):
    for x, y in tqdm(train_loader):
        opt.zero_grad()
        loss = loss_fn(model(x), y)
        loss.backward()
        opt.step()

"""#Test"""

# --- Test ---
correct = 0
with torch.no_grad():
    for x, y in tqdm(test_loader):
        pred = model(x).argmax(1)
        correct += (pred == y).sum().item()

print("Accuracy:", correct / len(test))