Seperate Triplet Loss
Open
- Dominant language
- Python
- Stars
- 620
- Forks
- 176
- PR merge metrics
- PR metrics pending
Description
请问在FramePipeline中直接将(n,m,d)输入seperate triplet loss，为何是seperate triplet loss，其seperate是每个scale的特征1个triplet loss吗？为何不直接像testing时拉直整个feature为(batch_size, hidden_dim)进而用1个“普通”的triplet loss？
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.