From the course: Introduction to Attention-Based Neural Networks

Unlock this course with a free trial

Join today to access over 24,700 courses taught by industry experts.

Loading in the Flickr8k dataset

Loading in the Flickr8k dataset

From the course: Introduction to Attention-Based Neural Networks

Start my 1-month free trial Buy for my team

Loading in the Flickr8k dataset

“

- We have CoLab set up. We have our dataset uploaded to Google Drive. We're ready to get started coding. Now, the name of this notebook is Image Captioning Without Attention because that's the model that we are going to build. We're going to look at images and try to generate captions for them using an RNN decoder but we will not use Attention. We'll look at the captions generated by this model and use that as a baseline for the next model where we will, indeed, use Attention to generate captions. The code that I've used here, in this demo is a modified version of the code available at this URL here on Kaggle and the data set for image captioning is also available on Kaggle at this link here. The Flickr 8k set. Now let's set up our import statements. You can see that I'm going to be building our neural network using PyTorch. You can see a number of imports for pandas and MAT plot lib. That is to load in…

Contents