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