amy-deng / dynamicgcn Goto Github PK

I don't see it in their website (https://dataverse.harvard.edu/dataverse/icews)

I have recently read this interesting paper， your github says there’s two kind of data， and I found the event data is semi-structured， however in your paper you demonstrate using several un-structured short text. So I guess you were using the news data? Is there any way I can access the datasets of four country in your paper?

Hello, did you not use ICEWS news data in your code?
Is the news data of Thailand collected by yourself, and then mark the occurrence of the incident?

Could you please tell me how did you select news data from a large amount of data?
Taking Thailand as an example, how were these 19,410 documents obtained from a total of 7 years of data from 2010 to 2016?

halo，how can i open file such as *.tx or *.x? Should i use visualization software?
thankyou!

TypeError: spmm() missing 1 required positional argument: 'matrix'
pytorch == 1.4.0
pytorch_sparse Refer to the official website to install

`--------------Parameters--------------
Namespace(batch=1, check_point=1, cuda=True, dataset='THAD6h', dropout=0.2, embedding='thailand', epochs=1000, f_dim=100, fastmode=False, lr=0.001, model='DynamicGCN', mylog=True, n_class=1, n_hidden=7, patience=10, seed=42, shuffle=True, tensorboard_log='', test=0.0, train=0.825, val=0.175, weight_decay=0.0005)

2020-09-16 08:25:59,920 CUDA status True
2020-09-16 08:25:59,923 tensorboard logging to tensorboard/THAD6h_100_DynamicGCN_1600215959_
2020-09-16 08:25:59,923 dimension of feature 100
load_w2v_emb data/thailand.emb_100
2020-09-16 08:26:43,998 load dataset THAD6h
2020-09-16 08:26:44,029 model DynamicGCN
total number of parameters: 149785
2020-09-16 08:26:44,032 training...
Traceback (most recent call last):
File "train.py", line 253, in
cur_acc = train(epoch, train_dict, val_dict, test_dict)
File "train.py", line 216, in train
output,_ = model(adj, idx)
File "/home/mll/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/data/mll/GraphNN/DynamicGCN/models.py", line 88, in forward
x = self.bn_stack[i](gcn_layer(x, adjs[i]))
File "/home/mll/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/data/mll/GraphNN/DynamicGCN/layers.py", line 39, in forward
output = spmm(adj._indices(),adj._values(), adj.size(0), support)
TypeError: spmm() missing 1 required positional argument: 'matrix'
`