Issues
- 7
CMU-MOSEI Experimentation Settings
#16 opened by ongdisheng - 2
What does the feature dimension represent?
#6 opened by hxl523 - 1
audio data
#5 opened by lileiooo - 0
- 0
P2FA是怎么搞的呀,python2里搞得吗
#21 opened by LuShanYanYu7 - 0
audio_data那里没看懂,传不传好像没区别吧
#22 opened by LuShanYanYu7 - 0
- 1
- 0
- 0
关于Masked Multimodal Attention的数据设置
#17 opened by Redredhorse - 2
- 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 by GitMonkey0 - 0
在run_classifier.py中的评估指标 acc7是什么
#13 opened by HXS572 - 0
ValueError: Output directory (Cross-Modal-BERT-master/CM-BERT_output) already exists and is not empty.
#12 opened by HXS572 - 1
FileNotFoundError: [Errno 2] No such file or directory: 'Cross-Modal-BERT-master/pre-trained BERT\\pytorch_model.bin'
#9 opened by HXS572 - 2
- 2
求一份将语音文件转为pickle文件的代码
#11 opened by HXS572 - 4
- 0
Trained model
#8 opened by MathildaSu - 6
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 by zhaohongwei1998 - 3
CMU-MOSEI data files
#1 opened by Astuary - 2
Fintune problem
#3 opened by cyZhu98 - 1
Question about data
#2 opened by leijue222