pytorch / pytorch/tutorials

Error in class Voc of chatbot_tutorial.py

Open
#554 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9.3k
Forks
4.4k
Avg merge
1d 21h
Merged PRs (30d)
4

Description

In the class Voc (line 283), the trim function(line 306) does not correctly reinitialize the word2count dictionary:

def trim(self, min_count):
        if self.trimmed:
            return
        self.trimmed = True

        keep_words = []

        for k, v in self.word2count.items():
            if v >= min_count:
                keep_words.append(k)

        print('keep_words {} / {} = {:.4f}'.format(
            len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index)
        ))

        # Reinitialize dictionaries
        self.word2index = {}
        self.word2count = {}
        self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
        self.num_words = 3 # Count default tokens

        for word in keep_words:
            self.addWord(word)

As the word2count dictionary is reinitialized, self.addWord(word) will only make all the word counts equal to 1, since keep_words will contain the unique words from word2count. The counts from the original conversations are lost. Could you please verify this?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in chatbot_tutorial.py around class Voc at line 283 and trim at line 306. Reproduce the behavior by comparing word counts before and after trimming, then verify that retained words preserve their original counts while excluded words are removed. Done when the tutorial's vocabulary trimming behavior matches the issue's expected count preservation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.