Issues
- 3
The dataset is unavailable now. Both direct download and wget not work. Could you please fix that?
#50 opened by sejmoonwei - 0
No data preprocessing
#52 opened by xihaad - 2
Data pre-processing
#44 opened by eatmorevegetables - 0
Can you share the hyperparameter configuration?
#51 opened by cyang810 - 7
the result is bad
#39 opened by fuziwang - 0
How to call models.py
#49 opened by userLx888 - 0
- 1
Transformer intermediate values
#28 opened by vandana-rajan - 5
Details about audio feature extraction
#25 opened by DesmonDay - 11
- 1
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
#46 opened by diaoyudiaochan - 0
The graphics card
#45 opened by liyuli1997 - 1
dataset
#43 opened by pipijiev12 - 0
dataset
#42 opened by pipijiev12 - 2
How can I set these hyperparameters?
#23 opened by ChenBattle - 2
Dataset download failed
#41 opened by yehaizhi - 1
Modal dimensions (audio, video) for the MOSI are different from values reported in paper?
#40 opened by souravBhat - 0
META information
#36 opened by vandana-rajan - 0
- 0
How does one go about using the model for inference?
#37 opened by ojss - 0
- 0
Padding mask
#34 opened by digbose92 - 0
Some question about evaluation metrics
#33 opened by zeroQiaoba - 16
- 7
The "mosei_senti_data_noalign.pkl" file you provide in dropbox cannot be unzipped correctly, it seems that the zip file is broken.
#31 opened by ppsk1ng - 1
GradientComputation Error
#30 opened by arminarj - 1
About 35 Facial Action Units
#29 opened by xingbow - 10
- 0
Classwise accuracy calculation
#27 opened by AnilRahate - 3
MOSEI dataset hyperparameters
#26 opened by JKBox - 5
Hyperparameters Setting
#5 opened by BinWang28 - 1
- 17
- 1
What is the maximum training length (in seconds) for unaligned mosei dataset ?
#21 opened by shamanez - 5
- 1
Links to the pretrained models
#19 opened by balloch - 2
Could I just use text&audio to train a model?
#18 opened by VirtualMoon - 10
How to train the network to obtain class accuracy for CMU-MOSIE sentiment data ?
#17 opened by shamanez - 1
how did you divide the Emocap dataset in to training , validation and testing ?
#16 opened by shamanez - 3
last_h_v = last_hs = h_vs[:,-1,:]
#14 opened by qniguoym - 1
buffered_future_mask
#15 opened by qniguoym - 4
- 0
- 1
- 8
KeyError: 'bytes104'
#10 opened by xiaoliqiangxxqzz - 2
multihead_attention.py
#9 opened by zouyi-ahu - 1
IEMOCAP Ddataset
#6 opened by BinWang28 - 1
Audio and Video features for MOSI
#4 opened by zsun227 - 1