Convolutional Autoencoder in Pytorch on MNIST dataset

Illustration by Author

The post is the seventh in a series of guides to build deep learning models with Pytorch. Below, there is the full series:

1. Pytorch Tutorial for Beginners
2. Manipulating Pytorch Datasets
3. Understand Tensor Dimensions in DL models
4. CNN & Feature visualizations
5. Hyperparameter tuning with Optuna
6. K Fold Cross Validation
7. Convolutional Autoencoder (this post)
8. Denoising Autoencoder
9. Variational Autoencoder

The goal of the series is to make Pytorch more intuitive and accessible as possible through examples of implementations. There are many tutorials on the Internet to use Pytorch to build many types of challenging models, but it can also be confusing at the same time because there are always slight differences when you pass from a tutorial to another. In this series, I want to start from the simplest topics to the more advanced ones.

Autoencoder

The autoencoder is an unsupervised deep learning algorithm that learns encoded representations of the input data and then reconstructs the same input as output. It consists of two networks, Encoder and Decoder. The Encoder compresses the…