Feedback about NLP From Scratch: Classifying Names with a Character-Level RNN
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9.3k
- Forks
- 4.4k
- Avg merge
- 1d 21h
- Merged PRs (30d)
- 4
Description
There is the following issue on this page: https://docs.pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html
I think that comment "#Cache the tensor representation of the labels" is a little confusing, especially for those who are just learning PyTorch, because you are just creating numerical representation of unique labels in alphabetical order, while calculating tensor representation of each label on every iteration of data.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Open the linked char_rnn_classification_tutorial.html page and locate the comment "Cache the tensor representation of the labels." Read the surrounding label-processing code, then revise the comment so it distinguishes the cached numeric label mapping from the per-example tensor conversion. Done means the comment accurately describes the behavior and is clearer for PyTorch learners.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 82/100