Low-rank-Multimodal-Fusion

Low-rank-Multimodal-Fusion copied to clipboard

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))"

1

Epoch 0 complete! Average Training loss: nan Training got into NaN values... Model initialized Epoch 0 complete! Average Training loss: nan Training got into NaN values... Model initialized Epoch 0...

xiajili

Can not pickle data

1

Hello, there is an error ' Cannot pickle local object 'load_mosi..MOSI',Is there a problem with the torch version?

Weiyinyin11

Hi, The train, test, valid numbers are not matching with the paper. And also, the pickle contains the binary labels. how do you run the scripts for multilabel. Can I...

padisarala

Cannot pickle dataset?

9

Can't pickle local object 'load_mosi..MOSI'

252057052

Thank you for sharing your work ! I'm confused about the data read from dataset IEMOCAP.pkl ` iemocap_data = pickle.load(open(data_path + "iemocap.pkl", 'rb'), encoding='bytes') print(np.sum(iemocap_data[b'happy'][TRAIN][TEXT])) print("------------------------------------") print(np.sum(iemocap_data[b'sad'][TRAIN][TEXT])) print("------------------------------------") print(np.sum(iemocap_data[b'angry'][TRAIN][TEXT])) print("------------------------------------")...

yuanjiechen

iemocap no key

2

train iemocap keyerror happy

songyh111

Some questions about mosi dataset.

1

Hello. How do you fix the nan and inf value in the mosi dataset? I just replace the inf value with 0, but the result is bad. Acc-2 is only...

Junge718

a question about train_pom.py

2

how to solve this problem?please Traceback (most recent call last): File "train_pom.py"， line 274, in main(PARAMS) File "train _pom.py", line 248, in main results = [ahid, vhid,thid，adr，vd, tdr，factor_lr，lr， x， batch_sz,...

qq291078365

i can't save model on colab

1

I tried to save this model on colab. model_save_name = 'classifier.pt' path = F"/content/gdrive/My Drive/{model_save_name}" torch.save(LMF.state_dict(), path) but found error TypeError Traceback (most recent call last) in () 1 model_save_name...

komalanadkat

Hi, There are two columns in the label field in the iemocap.pkl file and the value is only 0 and 1. Could you please provide me with information on whether...

calvin0205