thuiar/Cross-Modal-BERT

Issues

• CMU-MOSEI Experimentation Settings

  #16 opened 2 years ago by ongdisheng
  7

• What does the feature dimension represent?

  #6 opened 3 years ago by hxl523
  2

• audio data

  #5 opened 3 years ago by lileiooo
  1

• 您好，这里的audio特征是已经处理好的吗，没看到论文里使用的P2FA这部分的代码，我在这里遇到了困难

  #23 opened a year ago by LuShanYanYu7
  0

• P2FA是怎么搞的呀，python2里搞得吗

  #21 opened a year ago by LuShanYanYu7
  0

• audio_data那里没看懂，传不传好像没区别吧

  #22 opened a year ago by LuShanYanYu7
  0

• About the Visualization of the attention matrices.

  #20 opened a year ago by BaiMeiyingxue
  0

• Question regarding sequence lengths and padding masks

  #19 opened a year ago by raresionut1
  1

• pip install -r requirements.txt gives an error?

  #18 opened 2 years ago by paraanggotaforum
  0

• 关于Masked Multimodal Attention的数据设置

  #17 opened 2 years ago by Redredhorse
  0

• 数据集问题

  #14 opened 2 years ago by HXS572
  2

• 在本工作中，为了更公平的比较，我直接使用的CMU开源的特征文件。如果你想自己处理特征，请参考https://github.com/A2Zadeh/CMU-MultimodalSDK

  #15 opened 2 years ago by GitMonkey0
  2

• 在run_classifier.py中的评估指标 acc7是什么

  #13 opened 2 years ago by HXS572
  0

• ValueError: Output directory (Cross-Modal-BERT-master/CM-BERT_output) already exists and is not empty.

  #12 opened 2 years ago by HXS572
  0

• FileNotFoundError: [Errno 2] No such file or directory: 'Cross-Modal-BERT-master/pre-trained BERT\\pytorch_model.bin'

  #9 opened 2 years ago by HXS572
  1

• 关于文本标签的问题

  #10 opened 2 years ago by HXS572
  2

• 求一份将语音文件转为pickle文件的代码

  #11 opened 2 years ago by HXS572
  2

• 关于video数据

  #7 opened 3 years ago by SuN1775
  4

• Trained model

  #8 opened 2 years ago by MathildaSu
  0

• 没有处理视频数据的代码，数据只是传了进去，但是没有进行处理？？？

  #4 opened 3 years ago by zhaohongwei1998
  6

• CMU-MOSEI data files

  #1 opened 4 years ago by Astuary
  3

• Fintune problem

  #3 opened 3 years ago by cyZhu98
  2

• Question about data

  #2 opened 3 years ago by leijue222
  1