deepinsight / deepinsight/insightface
如何提高相同id特征的相似度评分
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
def cosin_metric(x1, x2):
return np.dot(x1, x2) / (np.linalg.norm(x1) * np.linalg.norm(x2))
我使用上述公式计算两个人脸特征的相似度评分，相同id的特征评分大约再0.4左右，请问有什么方法去提升这个评分，让它接近1？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the reported cosin_metric function and reproduce the approximately 0.4 score using same-ID face features. Then inspect the feature-extraction and comparison guidance in the repository to determine whether the score is expected and what a completed improvement would need to demonstrate.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- numpy, python
- 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