Add average pooling after conv-layer and combine it with existing max pooling.Change padding of conv-layer from same to valid.The char input ist optional and can be used for further reasearch. Combine word-level with character-based input.Add utils.py for moving code out of notebookīesides I made some changes in the jupyter notebook:.Add Yelp Polarity Dataset (Tensorflow-Dataset).Required data will be downloaded automatically. You can execute the notebook without any requirements. In this update I fixed some typos as well as improved the jupyter notebook. Changes *** UPDATE *** - September 10th, 2021 You can find the implementation of Yoon Kim on GitHub as well. My approach is quit similar to the one of Denny and the original paper of Yoon Kim. You can find a great introduction in a similar approach on a blog entry of Denny Britz and Keras. This project demonstrates how to classify text documents / sentences with CNNs. Text classification with Convolution Neural Networks (CNN)
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |