happynear / happynear/FaceVerification
你有试过把feature vector存下来，然后作为Siamese Network部分的输入，来单独训练Siamese部分吗，这样显存也许就不是问题了？
Open
- Dominant language
- MATLAB
- Stars
- 447
- Forks
- 230
- PR merge metrics
- No merged PRs in 30d
Description
Siamese部分的训练应该也不应该需要去跟新前面的weight吧
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or training entry point is named. First inspect the repository's Siamese Network training flow and how feature vectors are produced, then determine whether the requested workflow is technically defined; completion criteria are not specified in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- matlab
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100