Training an RNN to classify sequences using just the last LSTM output #325
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 7 commits
October 26, 2017 11:31
…the very end of training.
|
Hi aidan - just got back to town after a couple weeks abroad plus some insane paper deadline - looking forward to reviewing this properly. Thanks for the PR! |
ChaiBapchya
reviewed
Jan 22, 2020
ChaiBapchya
approved these changes
Jan 22, 2020
| " if len(s) > min_len and len(s) < max_len:\n", | ||
| " yield s\n", | ||
| " \n", | ||
| " # Run through all the novels and grab all the sentences in the books and grab all the sentences\n", |
There was a problem hiding this comment.
What do you mean here? @aidan-plenert-macdonald
There was a problem hiding this comment.
Just sentences out as series of characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I did this as a demo for a particular project. I can polish it up if you want it.
You basically just run an LSTM on every sequence, take the last output for each sequence and the push that through a neural net.
There are 2 demos training on generated data and then one classifying sentences as Spanish or English. The language one is tested using entirely different novels.