Notice: This page requires JavaScript to function properly.
Please enable JavaScript in your browser settings or update your browser.
Leer Challenge: Implementing Linear Regression | More Advanced Concepts
PyTorch Essentials
course content

Cursusinhoud

PyTorch Essentials

PyTorch Essentials

1. PyTorch Introduction
2. More Advanced Concepts
3. Neural Networks in PyTorch

book
Challenge: Implementing Linear Regression

Taak

Swipe to start coding

You are provided with a dataset that contains information about the number of hours students studied and their corresponding test scores. Your task is to train a linear regression model on this data.

  1. Convert these columns into PyTorch tensors, and reshape them to ensure they are 2D with shapes [N, 1].
  2. Define a simple linear regression model.
  3. Use MSE as the loss function.
  4. Define optimizer as SGD with the learning rate equal to 0.01.
  5. Train the linear regression model to predict test scores based on the number of hours studied. At each epoch:
    • Compute predictions on X_tensor;
    • Compute the loss;
    • Reset the gradient;
    • Perform backward pass;
    • Update the parameters.
  6. Access the model's parameters (weights and bias).

Oplossing

Switch to desktopSchakel over naar desktop voor praktijkervaringGa verder vanaf waar je bent met een van de onderstaande opties
Was alles duidelijk?

Hoe kunnen we het verbeteren?

Bedankt voor je feedback!

Sectie 2. Hoofdstuk 4
toggle bottom row

book
Challenge: Implementing Linear Regression

Taak

Swipe to start coding

You are provided with a dataset that contains information about the number of hours students studied and their corresponding test scores. Your task is to train a linear regression model on this data.

  1. Convert these columns into PyTorch tensors, and reshape them to ensure they are 2D with shapes [N, 1].
  2. Define a simple linear regression model.
  3. Use MSE as the loss function.
  4. Define optimizer as SGD with the learning rate equal to 0.01.
  5. Train the linear regression model to predict test scores based on the number of hours studied. At each epoch:
    • Compute predictions on X_tensor;
    • Compute the loss;
    • Reset the gradient;
    • Perform backward pass;
    • Update the parameters.
  6. Access the model's parameters (weights and bias).

Oplossing

Switch to desktopSchakel over naar desktop voor praktijkervaringGa verder vanaf waar je bent met een van de onderstaande opties
Was alles duidelijk?

Hoe kunnen we het verbeteren?

Bedankt voor je feedback!

Sectie 2. Hoofdstuk 4
Switch to desktopSchakel over naar desktop voor praktijkervaringGa verder vanaf waar je bent met een van de onderstaande opties
Onze excuses dat er iets mis is gegaan. Wat is er gebeurd?
some-alt