diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..d583158
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+data/
+runs/
\ No newline at end of file
diff --git a/loss.png b/loss.png
new file mode 100644
index 0000000..7b69d62
Binary files /dev/null and b/loss.png differ
diff --git a/main.py b/main.py
index dfe56fe..db0841d 100644
--- a/main.py
+++ b/main.py
@@ -14,4 +14,122 @@
 
 import numpy as np
 
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.utils.data import DataLoader
+from torchvision import datasets
+from torchvision.transforms import ToTensor
+
+from torch.utils.tensorboard import SummaryWriter
+
 # Your working code here
+
+training_data = datasets.CIFAR10(
+    root="data",
+    train=True,
+    download=True,
+    transform=ToTensor(),
+)
+
+test_data = datasets.CIFAR10(
+    root="data",
+    train=False,
+    download=True,
+    transform=ToTensor(),
+)
+
+
+batch_size = 64
+
+# Create data loaders.
+train_dataloader = DataLoader(training_data, batch_size=batch_size)
+test_dataloader = DataLoader(test_data, batch_size=batch_size)
+
+for X, y in test_dataloader:
+    print(f"Shape of X [N, C, H, W]: {X.shape}")
+    print(f"Shape of y: {y.shape} {y.dtype}")
+    break
+
+# Get cpu or gpu device for training.
+device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+print(f"Using {device} device")
+
+# Define model
+class NeuralNetwork(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.conv1 = nn.Conv2d(3, 6, 5)
+        self.pool = nn.MaxPool2d(2, 2)
+        self.conv2 = nn.Conv2d(6, 16, 5)
+        self.fc1 = nn.Linear(16 * 5 * 5, 120)
+        self.fc2 = nn.Linear(120, 84)
+        self.fc3 = nn.Linear(84, 10)
+
+    def forward(self, x):
+        x = self.pool(F.relu(self.conv1(x)))
+        x = self.pool(F.relu(self.conv2(x)))
+        x = torch.flatten(x, 1) # flatten all dimensions except batch
+        x = F.relu(self.fc1(x))
+        x = F.relu(self.fc2(x))
+        x = self.fc3(x)
+        return x
+
+model = NeuralNetwork().to(device)
+print(model)
+
+loss_fn = nn.CrossEntropyLoss()
+optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
+
+writer = SummaryWriter()
+
+def train(dataloader, model, loss_fn, optimizer):
+    size = len(dataloader.dataset)
+    model.train()
+    losses = []
+    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
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        if batch % 100 == 0:
+            loss, current = loss.item(), batch * len(X)
+            losses.append(loss)
+            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")
+    return np.mean(losses)
+
+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")
+    return test_loss
+
+epochs = 5
+for t in range(epochs):
+    print(f"Epoch {t+1}\n-------------------------------")
+    training_loss = train(train_dataloader, model, loss_fn, optimizer)
+    testing_loss = test(test_dataloader, model, loss_fn)
+
+    writer.add_scalar("Loss/train", training_loss, t)
+    writer.add_scalar("Loss/test", testing_loss, t)
+
+writer.close () 
+
+print("Done!")
\ No newline at end of file