Justin1904/Low-rank-Multimodal-Fusion
This is the repository for "Efficient Low-rank Multimodal Fusion with Modality-Specific Factors", Liu and Shen, et. al. ACL 2018
Python
Issues
- 0
The dataset link is invalid.
#27 opened by fhcgdtxnbhc - 2
Training got into NaN values...
#10 opened by hbzhang - 1
when I run "train_mosi.py", there is the below results with "UserWarning: dropout option adds dropout after all but last recurrent layer, so non-zero dropout expects num_layers greater than 1, but got dropout=0.3 and num_layers=1 "num_layers={}".format(dropout, num_layers))"
#25 opened by xiajili - 2
iemocap no key
#21 opened by songyh111 - 0
IEMOCAP labels
#26 opened by calvin0205 - 1
Can not pickle data
#23 opened by Weiyinyin11 - 0
iemocap dataset labels
#24 opened by padisarala - 9
Cannot pickle dataset?
#15 opened by 252057052 - 0
IEMOCAP datasets question
#22 opened by yuanjiechen - 1
Some questions about mosi dataset.
#20 opened by Junge718 - 2
a question about train_pom.py
#18 opened by qq291078365 - 1
i can't save model on colab
#19 opened by komalanadkat - 1
A question about formula (6)
#17 opened by oyss1996 - 3
AttributeError
#16 opened by frallisland - 1
is the implementation consistent with the math?
#14 opened by shalijiang - 1
what is z hat Equation (8)
#13 opened by shalijiang - 1
can we understand this method as a generalization of factorization machine?
#12 opened by shalijiang - 5
About the labels of IEMOCAP
#11 opened by yuki9965 - 4
about the learning rate
#9 opened by srtianxia - 8
- 4
Used for classification or to generate a tensor that reduces the amount of calculation?
#7 opened by Paidalin - 4
Epoch 0 complete! Average Training loss: nan
#8 opened by xiaoiker - 4
How many times did you use the 8895952 combination? How much time does each data set need to train?
#5 opened by Paidalin - 3
- 4
Best hyper-parameters settings
#1 opened by lan-qing - 2
Dimensions of data
#3 opened by kushagrajain11