dynamicgcn's People
Forkers
mindis yinyanting hanfengsunshine xianhuaxizi zwytop gaoli1537 surefirelin oceansnape yangbing668 gal0is zjdcts icarus-kch foreverqing xieck13 xiamenwcy xiaomu120413 dsi-lab1 kleeeeea voscar-zhang ikonushok yue-ning binchen4110 songgaojundengdynamicgcn's Issues
Where can I get the ICEWS news dataset?
I don't see it in their website (https://dataverse.harvard.edu/dataverse/icews)
This paper use ICEWS event data or ICEWS news data?
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?
about ICEWS news data
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?
How to select the news?
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?
file issue
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'
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'
`
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.