Practical: The training loop in PyTorch

In the linked Colab notebook we will use the simple network we created in week two to set up a training loop on some dummy data.

In the notebook we will cover the following:

• setting up an optimizer
• the steps that need to be performed in each pass of the training loop:
  • the forward pass
  • calculating the loss
  • the backward pass
  • updating the model weights using the optimizer
• setting up and using the training loop
• evaluating performance with a test function and validation data.

Follow the link below and work through the Colab notebook step by step.

The training loop in PyTorch

You may wish to open the link in a new browser tab so you can refer back here quickly.

Please leave any questions or comments below.