DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

Linear Regression in PyTorch

Buy Me a Coffee

*Memos:

  • My post explains Batch, Mini-Batch and Stochastic Gradient Descent with DataLoader() in PyTorch.
  • My post explains Batch Gradient Descent without DataLoader() in PyTorch.
  • My post explains Batch, Mini-Batch and Stochastic Gradient Descent.
  • My post explains how to save a model in PyTorch.
  • My post explains how to load a saved model in PyTorch.
  • My post explains Deep Learning Workflow in PyTorch.
  • My repo has models.

Linear Regression is the method to predict unknown data using another related known(true) data, making linear function as shown below:

*Memos:

import torch
from torch import nn
from torch import optim

# Set device
device = "cuda" if torch.cuda.is_available() else "cpu"

""" Prepare dataset """
weight = 0.8
bias = 0.5

X = torch.tensor([[0.00], [0.02], [0.04], [0.06], [0.08], # Size(50, 1)
                  [0.10], [0.12], [0.14], [0.16], [0.18],
                  [0.20], [0.22], [0.24], [0.26], [0.28],
                  [0.30], [0.32], [0.34], [0.36], [0.38],
                  [0.40], [0.42], [0.44], [0.46], [0.48],
                  [0.50], [0.52], [0.54], [0.56], [0.58],
                  [0.60], [0.62], [0.64], [0.66], [0.68],
                  [0.70], [0.72], [0.74], [0.76], [0.78],
                  [0.80], [0.82], [0.84], [0.86], [0.88],
                  [0.90], [0.92], [0.94], [0.96], [0.98]], device=device)
Y = weight * X + bias

l = int(0.8 * len(X))
X_train, Y_train, X_test, Y_test = X[:l], Y[:l], X[l:], Y[l:]
""" Prepare dataset """

""" Prepare model, loss function and optimizer """
class LinearRegressionModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear_layer = nn.Linear(in_features=1, out_features=1)

    def forward(self, x):
        return self.linear_layer(x)

    """ Without `nn.Linear()` """
    # def __init__(self):
    #     super().__init__()
    #     self.weight = nn.Parameter(torch.randn(1))
    #     self.bias = nn.Parameter(torch.randn(1))

    # def forward(self, x):
    #     return self.weight * x + self.bias
    """ Without `nn.Linear()` """

torch.manual_seed(42)

my_model = LinearRegressionModel().to(device)

loss_fn = nn.L1Loss()
# loss_fn = nn.MSELoss()

optimizer = optim.SGD(params=my_model.parameters(), lr=0.01)
# optimizer = optim.Adam(params=my_model.parameters(), lr=0.01)
""" Prepare model, loss function and optimizer """

""" Train and test model """
epochs = 100 # Try 0, 50, 100, 150

epoch_count = []
loss_values = []
test_loss_values = []

for epoch in range(epochs):

    """ Train """
    my_model.train()

    # 1. Calculate predictions(Forward propagation)
    Y_pred = my_model(X_train)

    # 2. Calculate loss
    loss = loss_fn(Y_pred, Y_train)

    # 3. Zero out gradients
    optimizer.zero_grad()

    # 4. Calculate a gradient(Backpropagation)
    loss.backward()

    # 5. Update parameters
    optimizer.step()
    """ Train """

    """ Test """
    my_model.eval()

    with torch.inference_mode():
        Y_test_pred = my_model(x=X_test)
        test_loss = loss_fn(Y_test_pred, Y_test)
    if epoch % 10 == 0:
        epoch_count.append(epoch)
        loss_values.append(loss)
        test_loss_values.append(test_loss)
        # print(f"Epoch: {epoch} | Loss: {loss} | Test loss: {test_loss}")
        # ↑ ↑ ↑ ↑ ↑ ↑ ↑ ↑ Uncomment it to see the details ↑ ↑ ↑ ↑ ↑ ↑ ↑ ↑
    """ Test """
""" Train and test model """

""" Visualize train and test data and predictions"""
import matplotlib.pyplot as plt

with torch.inference_mode():
    Y_pred = my_model(x=X_test)

def plot_predictions(X_train, Y_train, X_test, Y_test, predictions=None):
    plt.figure(figsize=[6, 4])
    plt.scatter(x=X_train, y=Y_train, c='g', s=5, label='Train data(Green)')
    plt.scatter(x=X_test, y=Y_test, c='b', s=15, label='Test data(Blue)')
    if predictions is not None:
        plt.scatter(x=X_test, y=predictions, c='r',
                    s=15, label='Predictions(Red)')
    plt.title(label="Train and test data and predictions", fontsize=14)
    plt.legend(fontsize=14)

plot_predictions(X_train=X_train.cpu(),
                 Y_train=Y_train.cpu(),
                 X_test=X_test.cpu(),
                 Y_test=Y_test.cpu(),
                 predictions=Y_pred.cpu())
""" Visualize train and test data, predictions"""

""" Visualize train and test loss """
def plot_loss_curves(epoch_count, loss_values, test_loss_values):
    plt.figure(figsize=[6, 4])
    plt.plot(epoch_count, loss_values, label="Train loss")
    plt.plot(epoch_count, test_loss_values, label="Test loss")
    plt.title(label="Train and test loss curves", fontsize=14)
    plt.ylabel(ylabel="Loss", fontsize=14)
    plt.xlabel(xlabel="Epochs", fontsize=14)
    plt.legend(fontsize=14)

plot_loss_curves(epoch_count=epoch_count,
                 loss_values=torch.tensor(loss_values).cpu(),
                 test_loss_values=torch.tensor(test_loss_values).cpu())
""" Visualize train and test loss """
Enter fullscreen mode Exit fullscreen mode

<L1Loss() and SGD()>

epochs = 0:

Image description

Image description

epochs = 50:

Image description

Image description

epochs = 100:

Image description

Image description

epochs = 150:

Image description

Image description

<MSELoss() and SGD()>

epochs = 0:

Image description

Image description

epochs = 50:

Image description

Image description

epochs = 100:

Image description

Image description

epochs = 150:

Image description

Image description

<L1Loss() and Adam()>

epochs = 0:

Image description

Image description

epochs = 50:

Image description

Image description

epochs = 100:

Image description

Image description

epochs = 150:

Image description

Image description

<MSELoss() and Adam()>

epochs = 0:

Image description

Image description

epochs = 50:

Image description

Image description

epochs = 100:

Image description

Image description

epochs = 150:

Image description

Image description

Image of Docusign

🛠️ Bring your solution into Docusign. Reach over 1.6M customers.

Docusign is now extensible. Overcome challenges with disconnected products and inaccessible data by bringing your solutions into Docusign and publishing to 1.6M customers in the App Center.

Learn more

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Explore a sea of insights with this enlightening post, highly esteemed within the nurturing DEV Community. Coders of all stripes are invited to participate and contribute to our shared knowledge.

Expressing gratitude with a simple "thank you" can make a big impact. Leave your thanks in the comments!

On DEV, exchanging ideas smooths our way and strengthens our community bonds. Found this useful? A quick note of thanks to the author can mean a lot.

Okay