yuetan031 / taddy_pytorch Goto Github PK

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?