TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Implementing a CNN for Text Classification in Tensorflow

92 pointsby dennybritzover 9 years ago

3 comments

cogwareover 9 years ago
Great tutorial - Well written and good patterns for TensorFlow usage, e.g. checkpointing, name scopes for cleaning up the graph visualization, and using summaries&#x2F;TensorBoard, and also nice explanations of the concepts.<p>Though I&#x27;m curious why you used VALID padding not SAME for the conv layers? It seems like it would be simpler to use SAME.<p>Also, minor nit: TensorFlow and TensorBoard should both have two letters capitalized
评论 #10724284 未加载
primaryobjectsover 9 years ago
Looks neat. Why did you bother using &lt;PAD&gt; words to have sentences be the same length, when you&#x27;re using a bag-of-words (document-term matrix) model anyway?<p>Each sentence vector ends up being the length of the vocabulary, so they&#x27;re already the same length. You can probably drop step #3 in this case.
评论 #10724372 未加载
nlover 9 years ago
This looks pretty nice. It&#x27;s worth pointing to the seq2seq TensorFlow example which covers a lot of similar topics.<p>Is there an example anywhere of how to initilize from the word2vec embeddings?
评论 #10725600 未加载