Multimodal-End2end-Sparse

Multimodal-End2end-Sparse copied to clipboard

ZhouJiaxin1

zbzbzzz

baseline运行加载数据时总是超出内存

9

调小batchsize没有用，请问如何让bseline模型不超内存呢

HEBAULC

RuntimeError: split_with_sizes expects split_sizes to sum exactly to 185 (input tensor's size at dimension 0), but got split_sizes=[83, 84]

3

Hi, When I try to run sparse MME2E with default settings according to ReadME, I got the following error. Can you help with it? Thanks in advance. RuntimeError: split_with_sizes expects...

jonnyhe

Hello, I have some question about this code,after we tokenizer the text transcription into tensor, when we use the model 'mme2e', it occurred the error below ,thanks for you help....

HOUSHIJING

about visual data extraction

1

we got problems when extracting visual data, the results we got is all 0 of IEMOCAP. We found it works when other videos but error when IEMOCAP. We tried download...

SteveTanggithub

请问这个是什么问题呢 问题出于 

wuyuhhhhh

Deer professor, I want to download the IEMOCAP dataset that you shared in oneDrive， it seems like need a password, could you send it to me ,thank you

wangjialin97

Hello! The link to the raw CMU-MOSEI dataset [http://immortal.multicomp.cs.cmu.edu/raw_datasets/CMU_MOSEI.zip] is no longer available, could you please share it?

LM-MSA

can't reproduce the paper's performance

1

Hi, Thank you very much for the code you shared. I tried to run the code with the following arguments: `python main.py -lr=5e-5 -ep=40 -mod=tav -bs=8 --img-interval=500 --early-stop=6 --loss=bce --cuda=3...

JYeonKim