torchdiy

A hobby project inspired by torch to learn how to design a deep learning framework.

This project also includes a DIY version of the torchdiy.transformers package, similar to Hugging Face's transformers.

Installation

To install the torchdiy package, run the following command:

$ pip install torchdiy

Running the Example

To run the example on the MNIST dataset, execute the following command:

$ python mnist.py

mnist.py file:

from torchvision import datasets, transforms
import torchdiy as torch

nn = torch.nn
optim = torch.optim
DataLoader = torch.utils.data.DataLoader

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.fc1 = nn.Linear(28 * 28, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, 10)
        self.relu = nn.ReLU()
        # self.dropout = nn.Dropout(0.5)

    def forward(self, x):
        x = x.view(-1, 28 * 28)
        x = self.relu(self.fc1(x))
        # x = self.dropout(x)
        x = self.relu(self.fc2(x))
        # x = self.dropout(x)
        x = self.fc3(x)
        return x

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)
        self.fc2 = nn.Linear(128, 10)
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        # self.dropout = nn.Dropout(0.5)

    def forward(self, x):
        x = self.relu(self.conv1(x))
        x = self.maxpool(x)
        x = self.relu(self.conv2(x))
        x = self.maxpool(x)
        x = x.view(-1, 64 * 7 * 7)
        x = self.relu(self.fc1(x))
        # x = self.dropout(x)
        x = self.fc2(x)
        return x

# model = CNN()
model = MLP()

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

num_epochs = 3
for epoch in range(num_epochs):
    model.train()
    running_loss = 0.0
    for i, (images, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if (i + 1) % 100 == 0:
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{i + 1}/{len(train_loader)}], Loss: {loss.item():.4f}')

    print(f'Epoch [{epoch + 1}/{num_epochs}], Loss: {running_loss / len(train_loader):.4f}')

model.eval()
correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'Accuracy of the model on the 10000 test images: {100 * correct / total:.2f}%')

torch.save(model.state_dict(), 'mnist_cnn.pth')

model.load_state_dict(torch.load('mnist_cnn.pth'))
model.eval()

with torch.no_grad():
    sample_image, true_label = test_dataset[0] 
    sample_image = sample_image.unsqueeze(0)
    output = model(sample_image)
    _, predicted = torch.max(output, 1)
    print(f'Predicted: {predicted.item()}, True Label: {true_label}')

Output example:

$ python mnist.py
Epoch [1/3], Step [100/938], Loss: 0.1205
Epoch [1/3], Step [200/938], Loss: 0.1729
...
Accuracy of the model on the 10000 test images: 96.92%
Predicted: 7, True Label: 7