Yuan Liu

[Feature]: Support BEiT Transformer layer

1

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

In distributed data parallel scenario, how can you guarantee the synchronization of memory bank in each process?

On MovieNet's website, there are 318 scene boundary annotated movies. Where can I find the 150 videos used in your experiments?

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Question about shape bias

1

Could you please provide the formula to get the shape bias? Currently, I can successfully run this repo with my own model, but I am confused about how the shape...

Hi, UCF101 contains train splits from 1 to 3 and test splits from 1 to 3, which train split and test split did you use to train and evaluate transfer...

Why there is negative index, e.g. -1, after the decoding of tokenizer?

Evaluation on traditional benchmark

1

Hi, could you please the code to evaluate the stage-1 and stage-2 model on tranditional benchmarks, e.g. VQA and Image Caption?

[Question] Instruction tuning data

3

### Question What are ``llava_instruct_80k.json`` and ``llava_instruct_150k.json`` used for? It seems they are not mentioned in the paper.