localminimum / localminimum/QANet
conv_block problem
Open
- Dominant language
- Python
- Stars
- 985
- Forks
- 297
- PR merge metrics
- No merged PRs in 30d
Description
Why is the dropout here not every resudial block?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by locating the conv_block implementation and compare it with the QANet layers shown in the attached image. Determine whether dropout is intentionally limited to the shown residual blocks; the issue is complete when that behavior is explained or the discrepancy is identified for correction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100