Open MischaQI opened 3 years ago
Sorry, we haven't provided fine-tuning code yet.
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?
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.
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?
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.
when will the fine_tuning code be releaseed? thanks
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?