Handy Google Colab notebook for Cats and Dogs classification exercise

Summary

The provided content offers a modified Google Colab notebook for the Udacity PyTorch Scholarship Challenge course, specifically for the Lesson 4 exercise in classifying cat and dog images using GPU acceleration.

Abstract

The web content introduces a Google Colab notebook tailored for participants of Udacity's "Deep Learning with PyTorch" course, focusing on the classification of cat and dog images in Lesson 4. This exercise necessitates GPU access, which is facilitated through Google Colab, a free platform that provides GPU support. The author has prepared a notebook with necessary modifications to streamline the process: it includes the installation of PyTorch version 0.4, configuration for GPU runtime, automatic dataset download and extraction, and integration of helper functions from helper.py. The steps to use the notebook are clearly outlined, from downloading it via a provided link to uploading it to Google Colab and executing it. The author encourages users to reach out on Slack for assistance and expresses well-wishes for successful completion of the exercise.

Opinions

The author believes that using Google Colab is a beneficial alternative for those without access to a GPU.
They express confidence that their modifications will help users focus on the exercise rather than the setup process.
The author is open to providing support, inviting users to contact them on Slack if they encounter any issues.
They imply that integrating the helper methods into the notebook is more convenient than uploading the helper.py file separately.

Handy Google Colab notebook for Cats and Dogs 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 images of Dogs and Cats. 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

I did following to download the dataset:

!wget -c https://s3.amazonaws.com/content.udacity-data.com/nd089/Cat_Dog_data.zip

!unzip -qq Cat_Dog_data.zip

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!