yuetan031 / taddy_pytorch Goto Github PK
View Code? Open in Web Editor NEWA Pytorch implement of paper "Anomaly detection in dynamic graphs via transformer" (TADDY).
License: MIT License
A Pytorch implement of paper "Anomaly detection in dynamic graphs via transformer" (TADDY).
License: MIT License
作者您好,我是一名**的研究生,我想问一下这个代码的eigen文件在哪里可以下载
Hi, I am running your code with the command:
python 1_train.py --dataset uci --anomaly_per 0.1
after running:
python 0_prepare_data.py --dataset uci
And it shows that 'data/eigen/uci_0.5_0.1.pkl' not found, so I make a copy the same as which in the 'data/percent' folder. Is that correct?
But actually I run into a bug with the traceback:
$$$$ Start $$$$ Loading uci dataset... Loading eigen from: data/eigen/uci_0.5_0.1.pkl Traceback (most recent call last): File "1_train.py", line 56, in <module> setting_obj.run() File "/home/syj/syj_project/TADDY_pytorch/codes/Settings.py", line 8, in run loaded_data = self.dataset.load() File "/home/syj/syj_project/TADDY_pytorch/codes/DynamicDatasetLoader.py", line 173, in load adjs, eigen_adjs = self.get_adjs(rows, cols, weights, nb_nodes) File "/home/syj/syj_project/TADDY_pytorch/codes/DynamicDatasetLoader.py", line 134, in get_adjs eigen_adjs.append(np.array(eigen_adj_sparse.todense())) AttributeError: 'list' object has no attribute 'todense'
And I totally have no idea why eigen_adj_sparse is a list?
Could you please help me wtih this? Thanks in advance.
PS: actually my running environment matches yours.
File "C:\Users\16645\Desktop\代码\Anomaly Detection in Dynamic Graphs via\1_train.py", line 56, in
setting_obj.run()
File "C:\Users\16645\Desktop\代码\Anomaly Detection in Dynamic Graphs via\codes\Settings.py", line 8, in run
loaded_data = self.dataset.load()
File "C:\Users\16645\Desktop\代码\Anomaly Detection in Dynamic Graphs via\codes\DynamicDatasetLoader.py", line 173, in load
adjs, eigen_adjs = self.get_adjs(rows, cols, weights, nb_nodes)
File "C:\Users\16645\Desktop\代码\Anomaly Detection in Dynamic Graphs via\codes\DynamicDatasetLoader.py", line 142, in get_adjs
adj = sp.csr_matrix((weights[i], (rows[i], cols[i])), shape=(nb_nodes, nb_nodes), dtype=np.float32)
File "C:\aconda\envs\python38\lib\site-packages\scipy\sparse\compressed.py", line 54, in init
other = self.class(coo_matrix(arg1, shape=shape))
File "C:\aconda\envs\python38\lib\site-packages\scipy\sparse\coo.py", line 196, in init
self._check()
File "C:\aconda\envs\python38\lib\site-packages\scipy\sparse\coo.py", line 283, in _check
raise ValueError('row index exceeds matrix dimensions')
Somone make it work nowadays?
`def get_adjs(self, rows, cols, weights, nb_nodes):
eigen_file_name = 'data/eigen/' + self.dataset_name + '_' + str(self.train_per) + '_' + str(self.anomaly_per) + '.pkl'
if not os.path.exists(eigen_file_name):`
Hello author, the above data set is missing in your code.
Hello,
based on your code and paper, only topological time dependent Embeddings are generated. In the case of Network Intrusion Detection, for example, edge features are important to integrate in the embeddings. Is there a way to extend your model, so that it can also handel node/edge features?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.