Home / IT & Computer Science / Biology & Biotechnology / Deep Learning for Bioscientists / Practical: regression in PyTorch
Practical: regression in PyTorch
A link to a Colab notebook giving a worked example of a deep learning network performing a regession counting the number of flower heads in images
© The University of Nottingham
How do we adjust a CNN for use in a regression problem rather than classification?
In the linked Colab notebook we will take the image classifier we created in the previous practical, and convert it to a regression task that aims to count the number of flowers in each picture.
In the notebook we will cover the following:
- setting up the dataset for use with our new regression problem
- adjusting the “off-the-shelf” ResNet we used for the image classifier to count the number of flower heads rather than identify different species
- checking the performance of the regression model using a simple plot.
Follow the link below and work through the Colab notebook step by step.
A simple regression problem in PyTorch
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.
