Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How to Build Custom Datasets for Text in PyTorch

Aladdin Persson via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to build custom datasets for text processing in PyTorch with this in-depth tutorial video. Explore advanced techniques for handling text data using an image captioning dataset (Flickr8k) as an example. Discover how to implement a PyTorch Dataset for loading Flickr data, set up vocabulary and numericalization, create collate functions for batch padding, and develop a function for obtaining data loaders. Apply these principles to various text-based projects, including translation, question answering, and sentiment analysis. Follow along as the instructor demonstrates the code implementation, troubleshoots errors, and provides valuable insights for working with text data in PyTorch.

Syllabus

- Introduction
- Overview of what we're going to do
- Imports
- Setup of Pytorch Dataset for loading Flickr
- Setup of Vocabulary and Numericalization
- Creating Collate for Padding of Batch
- Function for getting data loader
- Running code & fixing couple of errors
- Ending

Taught by

Aladdin Persson

Reviews

Start your review of How to Build Custom Datasets for Text in PyTorch

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.