how much GPU memory does the next QA need?

[vacuum-cup]

No description provided.

[doc-doc]

Thanks for the question. It needs about 24G for training of the model with batch size 64 with 8 clips for each video, whereas 8G is enough for inference. If you want to train with 16 clips, you need to change batchsize to 32.

[vacuum-cup]

Thank you for your reply.

[vacuum-cup]

Well，Could you offer the pre-trained bert model？ Thanks.

[LemonQC]

Well, I also need this

[doc-doc]

Hi, please find the code and mode for BERT finetuning/feature extraction. You should launch a new issue with a proper title, otherwise I may slow in finding your questions..

[LemonQC]

ok, many thanks. Is the model in nextqa for question features the final model? Or I still need to train? I just utilize the model to extract question feature while the results drop significantly by nearly 5 points.