RAVEN

RAVEN copied to clipboard

RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 300 and 0 in dimension 1

2

``` def __getitem__(self, index): inputLen = self.wordLength[index] return torch.cat((torch.tensor(self.wordInput[index], dtype=torch.float32), torch.zeros((gc.padding_len - len(self.wordInput[index]), gc.wordDim))), 0),\ torch.cat((torch.tensor(self.covarepInput[index], dtype=torch.float32), torch.zeros((gc.padding_len - len(self.covarepInput[index]), gc.shift_padding_len, gc.covarepDim))), 0),\ torch.cat((torch.tensor(self.covarepLength[index], dtype=torch.long), torch.zeros(gc.padding_len - len(self.covarepLength[index]), dtype=torch.long)), 0),\...

gjyao

Understanding the LSTM models

4

I have read your paper and it is very interesting. I understood that you used last layer features of LSTM networks for combination with language vectors. However, would you please...

ShirinVafaei

file missing

3

dataset = "iemocap" data_path = None raw_path = None if dataset == "MOSI": data_path = "/home/data/wangyansen/cmumosi/" elif dataset == "iemocap": data_path = "/media/bighdd7/yansen/code/tools/iemocap/" raw_path = "/media/bighdd4/Paul/mosi2/experiments/iemocap/" def get_data(): print("fetching labels...")...

jiaolifengmi

Could you please point out that how to get the labels_old.p file? (We have the original dataset IEMOCAP_full_release downloaded already.)

sddai

def readFromCSD(self): labelCompSeq = computational_sequence(self.root+'CMU_MOSI_Opinion_Labels.csd').data facetCompSeq = computational_sequence(self.root+'CMU_MOSI_VisualFacet_4.1.csd').data wordCompSeq = computational_sequence(self.root+'CMU_MOSI_TimestampedWordVectors.csd').data covarepCompSeq = computational_sequence(self.root+'CMU_MOSI_COVAREP.csd').data Where can I find the third data(CMU_MOSI_TimestampedWordVectors.csd).Only thre 'CMU_MOSI_TimestampedWords' I can find.Looking forward to your reply.

rick-mondy

raw_MOSI data missing?

3

No word2ix_300_mosi.pkl?

songxujing

data

1

truth_path = dataset_path + 'Meta_data/boundaries_sentimentint_avg.csv' #openface_path = dataset_path + "Features/Visual/OPEN_FACE/Segmented/" openface_path = dataset_path + "Features/Visual/OpenfaceRaw/" facet_path = dataset_path + "Features/Visual/FACET_GIOTA/" covarep_path = dataset_path + "Features/Audio/raw/" transcript_path = dataset_path + 'Transcript/SEGMENT_ALIGNED/'...

songxujing