Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

Chapter 4
Classifying Images
Spoilers
In this chapter, we will:
• build models to classify images
• use Torchvision to apply transformations to images
• compose transformations and apply them to datasets
• perform data augmentation in the training set
• use samplers to handle imbalanced datasets
• understand why we need activation functions
• build a deeper model using activation functions
Jupyter Notebook
The Jupyter notebook corresponding to Chapter 4 [76] is part of the official Deep
Learning with PyTorch Step-by-Step repository on GitHub. You can also run it
directly in Google Colab [77] .
If you’re using a local installation, open your terminal or Anaconda prompt and
navigate to the PyTorchStepByStep folder you cloned from GitHub. Then, activate
the pytorchbook environment and run jupyter notebook:
$ conda activate pytorchbook
(pytorchbook)$ jupyter notebook
If you’re using Jupyter’s default settings, this link should open Chapter 4’s
notebook. If not, just click on Chapter04.ipynb in your Jupyter’s home page.
Imports
For the sake of organization, all libraries needed throughout the code used in any
given chapter are imported at its very beginning. For this chapter, we’ll need the
following imports:
Spoilers | 265