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

TLDR; here is the link to the modified notebook — https://drive.google.com/open?id=1RacHDFpDvKPxN4brmGMnEY2454CW_Dds

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:

1. Download the modified Notebook from this link
2. Visit Google Colab
3. You will be prompted with a modal, select Upload
4. If modal doesn’t appear and instead if it opens a new Notebook, then from menu File > Upload Notebook
5. Upload the modified notebook
6. 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:

1. Intsall PyTorch v.0.4
2. Set the Runtime to GPU, so that GPU is enabled
3. Download the dataset and unzip it
4. 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!