Spoilers

What to expect from this chapter

In this chapter, we will:

• Build a function to perform training steps.
• Implement our own dataset class.
• Use data loaders to generate mini-batches.
• Build a function to perform mini-batch gradient descent.
• Evaluate our model.
• Integrate TensorBoard to monitor model training.
• Save/checkpoint our model to disk.
• Load our model from disk to resume training or to deploy.