update

readme.md

@@ -9,13 +9,14 @@ python ./run.py
 you can train the model by `run.py`
 
 ## requirement
-TensorFlow==1.15.4
+```text
-dppy==0.2.0
+TensorFlow==1.15.4  
-munkres
+dppy==0.2.0  
-scikit-learn
+munkres  
-cvxopt
+scikit-learn  
-> `cvxopt` requires `Numpy-MKL`, you can get the windows binary [here](http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy).  
+cvxopt  
-> And install the `cvxopt` binary from [here](http://www.lfd.uci.edu/~gohlke/pythonlibs/#cvxopt)
+```
+> `cvxopt` requires `Numpy-MKL`, you can get the windows binary [here](http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy). And install the `cvxopt` binary from [here](http://www.lfd.uci.edu/~gohlke/pythonlibs/#cvxopt)
 
 ## acknowledge
 Thanks for the projects **GAT：** [https://github.com/PetarV-/GAT](https://github.com/PetarV-/GAT)

settings.py

@@ -29,7 +29,6 @@ seed = 7
 np.random.seed(seed)
 tf.set_random_seed(seed)
 
-
 def get_settings(dataname, model, task):
     if dataname != 'citeseer' and dataname != 'cora' and dataname != 'pubmed':
         print('error: wrong data set name')