Understanding one-dimensional convolution for sequence data 

In Chapter 5Deep Learning for Computer Vision, we have seen how two-dimensional weights are learned from the training data. These weights move across the image to generate different activations. In the same way, one-dimensional convolution activations are learned during training of our text classifier, where these weights learn patterns by moving across the data. The following diagram explains how one-dimensional convolutions will work:

For training a text classifier on the IMDB dataset, we will follow the same steps as we followed for building the classifier using LSTM. The only ...

Get Deep Learning with PyTorch now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.