Handy Google Colab notebook for MNIST Digits classification exercise (Lesson 4)

Summary

The website provides a modified Google Colab notebook for the MNIST Digits classification exercise in Udacity's PyTorch Scholarship Challenge course, which allows users to utilize a GPU for free.

Abstract

The undefined website offers a practical solution for participants of Udacity's PyTorch Scholarship Challenge, specifically for Lesson 4's MNIST digit classification exercise. Recognizing that many users may not have access to a GPU, the site's author, Avinash, has created a Google Colab notebook that can be used with GPU support. The notebook is available for download from a provided Google Drive link and includes all necessary modifications for direct use on Google Colab. The steps to use the notebook are clearly outlined, from downloading and uploading it to Colab, to executing the exercise without the need for manual dataset downloads or additional file uploads. The author has also listed the changes made to the original notebook, such as installing a specific version of PyTorch, enabling GPU runtime, and integrating methods from helper.py. The author encourages users to reach out on Slack for assistance with the notebook.

Opinions

The author believes that using Google Colab is a beneficial alternative for those without access to a GPU.
The author is committed to helping others, as evidenced by providing their Slack username for support.
The author assumes that users may struggle with setting up the environment for the exercise, hence the creation of the modified notebook.
The author is optimistic that the provided notebook will help users focus on the exercise rather than the setup process.

Handy Google Colab notebook for MNIST Digits classification exercise (Lesson 4)

This blog post is for people who are doing Udacity’s PyTorch Scholarship Challenge course: Deep Learning with PyTorch.

In Lesson 4, we get to classify handwritten digits from MNIST database. This exercise requires access to a GPU. Since not many of us do not have a GPU, a good and free alternative is Google Colab.

So, I created this notebook with all the modifications required so that you can run this on Colab directly. Here are the brief steps:

Download the modified Notebook from this link

Visit Google Colab

You will be prompted with a modal, select Upload

If modal doesn’t appear and instead if it opens a new Notebook, then from menu File > Upload Notebook

Upload the modified notebook

That’s it!

Now you can focus on completing the exercise instead of worrying about how to download the images etc.

If you are interested in knowing changes I have made:

Intsall PyTorch v.0.4

Set the Runtime to GPU, so that GPU is enabled

Download the dataset and unzip it

Add the methods from helper.py so that you don’t need to upload it

Hope this helps! If you have got any issues with running this notebook, then feel free to message me on Slack for any help. My slack username is avinash

All the best for the exercise!