train.py

import torch
import torch.nn as nn
from torch.utils.data import TensorDataset, DataLoader, random_split
from model import NeuralNetwork

if torch.cuda.is_available():
    device = torch.device("cuda")
elif torch.backends.mps.is_available():
    device = torch.device("mps")
else:
    device = torch.device("cpu")

model = NeuralNetwork().to(device)
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)

# Dataset will be 50000 data points with 10 feature inputs
N, d_in = 50000, 10
X = torch.randn(N, d_in)

# Instead of fully random labels, we will have a simple relationship that the neural network >
# The relationship (first part) is that the label = 1 if sum of features > 0, else 0
# We then add a bit of noise by flipping 5% of the labels (second part) so it's more realistic
y = ((X.sum(dim=1) > 0).long() ^ (torch.rand(N) < 0.05).long())

dataset = TensorDataset(X, y)

n_train = int(0.8 * N)
n_test = N - n_train
train_ds, test_ds = random_split(dataset, [n_train, n_test])

train_dataloader = DataLoader(train_ds, batch_size=32, shuffle=True)
test_dataloader = DataLoader(test_ds, batch_size=128, shuffle=False)

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")