In [1]:
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
In [2]:
# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
In [3]:
# Hyper-parameters 
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001
In [4]:
# MNIST dataset 
train_dataset = torchvision.datasets.MNIST(root='../../data', 
                                           train=True, 
                                           transform=transforms.ToTensor(),  
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data', 
                                          train=False, 
                                          transform=transforms.ToTensor())
In [9]:
# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, 
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset, 
                                          batch_size=batch_size, 
                                          shuffle=False)
In [11]:
# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size) 
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)  
    
    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out
In [13]:
model = NeuralNet(input_size, hidden_size, num_classes).to(device)
In [15]:
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)  
In [17]:
# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):  
        # Move tensors to the configured device
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)
        
        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
Epoch [1/5], Step [100/600], Loss: 0.2807
Epoch [1/5], Step [200/600], Loss: 0.2587
Epoch [1/5], Step [300/600], Loss: 0.1431
Epoch [1/5], Step [400/600], Loss: 0.1042
Epoch [1/5], Step [500/600], Loss: 0.1094
Epoch [1/5], Step [600/600], Loss: 0.0942
Epoch [2/5], Step [100/600], Loss: 0.1129
Epoch [2/5], Step [200/600], Loss: 0.1657
Epoch [2/5], Step [300/600], Loss: 0.0813
Epoch [2/5], Step [400/600], Loss: 0.1026
Epoch [2/5], Step [500/600], Loss: 0.0576
Epoch [2/5], Step [600/600], Loss: 0.1254
Epoch [3/5], Step [100/600], Loss: 0.0597
Epoch [3/5], Step [200/600], Loss: 0.0452
Epoch [3/5], Step [300/600], Loss: 0.0943
Epoch [3/5], Step [400/600], Loss: 0.0997
Epoch [3/5], Step [500/600], Loss: 0.0445
Epoch [3/5], Step [600/600], Loss: 0.0866
Epoch [4/5], Step [100/600], Loss: 0.0914
Epoch [4/5], Step [200/600], Loss: 0.0646
Epoch [4/5], Step [300/600], Loss: 0.0601
Epoch [4/5], Step [400/600], Loss: 0.0155
Epoch [4/5], Step [500/600], Loss: 0.0455
Epoch [4/5], Step [600/600], Loss: 0.0547
Epoch [5/5], Step [100/600], Loss: 0.0772
Epoch [5/5], Step [200/600], Loss: 0.0442
Epoch [5/5], Step [300/600], Loss: 0.0329
Epoch [5/5], Step [400/600], Loss: 0.0339
Epoch [5/5], Step [500/600], Loss: 0.0457
Epoch [5/5], Step [600/600], Loss: 0.0323
In [23]:
# Test the model
# In test phase, we don't need to compute gradients 
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
Accuracy of the network on the 10000 test images: 97.86 %
In [25]:
# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')
In [ ]: