search

thuiar / Cross-Modal-BERT

CM-BERT: Cross-Modal BERT for Text-Audio Sentiment Analysis（MM2020）
100 stars 26 forks source link

CMU-MOSEI Experimentation Settings #16

Open ongdisheng opened 1 year ago

ongdisheng commented 1 year ago

Hi @Kaicheng-Yang0828,

I have tried to run CM-BERT on CMU-MOSEI dataset. However, I only manage to get around 74.15 for acc2 instead of 83.6 as mentioned in https://github.com/thuiar/Cross-Modal-BERT/issues/1#issuecomment-843100902.

Below are the steps that I have taken:

  1. Changed audio pickle file from MOSI_cmu_audio_CLS.pickle to MOSEI_cmu_audio_CLS.pickle

  2. Changed dev, test and train tsv files to hold CMU-MOSEI data

  3. Modified loaded pickle file to MOSEI_cmu_audio_CLS.pickle in _runclassifier.py file image

  4. Modified dimension of audio modality from 5 to 74 in model.py file image

Is there any step that I have done wrongly or missed out? Just wondering is it also possible to have the code files for CMU-MOSEI too?

Your help is very much appreciated. Thanks!

Chaos2Byte commented 1 year ago

Have you solved it yet?

ongdisheng commented 1 year ago

Unfortunately no

Tahasin-tech commented 1 year ago

Unfortunately no

Have you solved it yet?

ongdisheng commented 1 year ago

Nope, I still couldn't figure it out

ingtaoLi commented 10 months ago

Hello, I am sorry to hear this news. Do you have the file MOSEI_cmu_audio_CLS.pickle? The http://immortal.multicomp.cs.cmu.edu/raw_datasets/processed_data/ URL posted by the author has expired. Can you share this file with me? good luck!

kirakira0703 commented 6 months ago

你好，请问可以分享一下MOSEI_cmu_audio_CLS.pickle吗？官方的这个数据貌似不共享了

ingtaoLi commented 6 months ago

好，请问可以分享一下MOSEI_cmu_audio_CLS.pickle吗？官方的这个数据你不分享了

后面我没有找到官方的文件，但是你可以参考同样是清华大学发布的https://drive.google.com/drive/folders/1A2S4pqCHryGmiqnNSPLv7rEg63WvjCSk?usp=sharing中的MOSEI数据集，并修改相应的代码即可进行模型的训练， 我与@ongdisheng最后进行实验的结果相似， Acc-2指标仅有73.7，Acc-7仅有51.8，F1值74.2。