Mismatch between Fig. 4 (Feature Extractor Module) of paper and implementaion
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 829
- Forks
- 138
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 1
Description
Hi and thanks for your great work
In figure 4 of the paper, we have this diagram for Feature Extractor module:
The second part (four DC block) takes $F_{t-1}^e$ as input right? but in the implementation:
def forward(self, x, quant):
x1, ctx_t = self.forward_part1(x, quant)
ctx = self.forward_part2(x1)
return ctx, ctx_t
you passed x1 (output of first part BEFORE multiplying by $q_f$
why?
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
Start by comparing Fig. 4 of the paper with the feature extractor's forward method, including the forward_part1 and forward_part2 calls and the point where q_f is applied. Determine whether the implementation matches the diagram or whether the diagram needs clarification; done means the discrepancy is resolved and documented or corrected with supporting tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 32/100