zhanghang1989 / zhanghang1989/PyTorch-Encoding
The inconsistent between the implementation and original paper of EncNet
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
When I check the source code of EncNet, I found
F.relu_(x + x * y). Does that mean the attention similar to residual attention? It is different from the framework in original paper. I hope to get the correct explanation.
Contributor guide
No contributing guide indexed for this repository
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
Start by locating the EncNet implementation containing F.relu_(x + x * y) and compare that operation with the framework described in the original paper. Determine whether the difference is intentional and document a clear explanation of the relationship between the implementation and the paper.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100