-
Hi,
In my data, each query has one positive example and multiple examples.
an example looks like this,
Query1, positive s0, negative s1, negative s2..., label is 1,0,0...
Query2, negative s0…
-
你好，请教下，就是加入local分支训练后，相对于只用triplet loss训练原始Resnet50性能只提升一个点吗？
-
I would like to thank you very much for continually adding new, practical RIFE models. For this last one I am particularly grateful to you. Firstly because you are open to the work of others that can …
AIVFI updated
5 months ago
-
Out of curiosity (and for a comparison to [Tevatron](https://github.com/texttron/tevatron/tree/main)) I tried running the [MSMarco MRNL](https://github.com/UKPLab/sentence-transformers/blob/master/exa…
-
Dear Dr.Xiang,
When I execute the commond line "sh make.sh", I met some errors as follow. Could you give me some advise with these errors?
Assembler messages:
Fatal error: can't create computin…
-
## T5-Generation Fine-tuning Task
### Data Preparation
- can only use specially-preprocessed: speaker-spec dataset, because the max input length for t5 is 512.
- preprocessing
1. `lib/create…
-
Hi Everyone,
Thank you for your continuous efforts, I'm really enjoying the new release.
One confusing concept for me is the CachedGISTEmbedLoss, CachedMultipleNegativesRankingLoss
From what…
-
The README.md wrote:
> This repo provides a comprehensive face recognition library for face related analytics \& applications, including face alignment (detection, landmark localization, affine tra…
-
Maybe it is a naive questions (as I am not native to pyTorch).
When training as an example shown here (to the above loss mentioned):
```
model = SentenceTransformer('distilbert-base-nli-mean-to…
-
# Resumo
Iniciei a implementação dos experimentos visando reproduzir #59, mas estava encontrado dificuldades em fazer o código do zero, com muitas informações vagas do artigo. Contudo, descobri que…