Giters

BAAI-WuDao / BriVL

Bridging Vision and Language Model

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Fine-tuning code

MischaQI opened this issue · comments

commented

I used the provided pre-trained BriVL model to obtain the text and image embeddings for classification tasks, but the results are dissatisfactory. Will the fine-tuning code be provided?

commented

Sorry, we haven't provided fine-tuning code yet.

commented

I used the provided pre-trained BriVL model to obtain the text and image embeddings for classification tasks, but the results are dissatisfactory. Will the fine-tuning code be provided?

OOI, have you tried other model that has better performance?

commented

I used the provided pre-trained BriVL model to obtain the text and image embeddings for classification tasks, but the results are dissatisfactory. Will the fine-tuning code be provided?

OOI, have you tried other model that has better performance?

CLIP(https://github.com/openai/CLIP) performs quite well on my task.

commented

I used the provided pre-trained BriVL model to obtain the text and image embeddings for classification tasks, but the results are dissatisfactory. Will the fine-tuning code be provided?

OOI, have you tried other model that has better performance?

CLIP(https://github.com/openai/CLIP) performs quite well on my task.

🤔 isn't BriVL trained on Chinese but CLIP trained on English?

commented

I used the provided pre-trained BriVL model to obtain the text and image embeddings for classification tasks, but the results are dissatisfactory. Will the fine-tuning code be provided?

OOI, have you tried other model that has better performance?

CLIP(https://github.com/openai/CLIP) performs quite well on my task.

🤔 isn't BriVL trained on Chinese but CLIP trained on English?

If you are talking about Chinese datasets, I have not found other well-performing pre-trained VL models.

commented

when will the fine_tuning code be releaseed? thanks