Spoilers

What to expect from this chapter

In this chapter, we will:

• Briefly review the steps of gradient descent (optional).

• Use gradient descent to implement a linear regression in Numpy.

• Create tensors in PyTorch (finally!).

• Understand the difference between CPU and GPU tensors.

• Understand PyTorch’s main feature, autograd, to perform automatic differentiation.

• Visualize the dynamic computation graph.

• Create a loss function.

• Define an optimizer.

• Implement our own model class.

• Implement nested and sequential models using PyTorch’s layers.