Practical: Building a simple CNN
A link to a colab notebook demonstrating how to build simple convolutional neural networks in PyTorch
© The University of Nottingham
PyTorch does contain some ‘off the shelf’ networks ready for use, but here we will look at how to build a simple convolutional nearal network from scratch.
In the linked Colab notebook we will look at the following:
- objects and classes
- the PyTorch
moduleclass - defining trainable layers, such as convolutional layers
- adding other layers, such as max pooling layers, and adding activation functions
- linking layers and activation functions together into a network
- how to intialise run a forward pass through the network.
Follow the link below and work through the Colab notebook step by step.
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.
Reach your personal and professional goals
Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.
Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.
