pygcn
pygcn copied to clipboard
tkipf
Graph Convolutional Networks in PyTorch
To #58, the results are not reproducible. It's caused by the one-hot encoding for the label while loading the data. We can get reproducible results after fixing the class order.
I see the code in utils.py idx_train = range(140) idx_val = range(200, 500) idx_test = range(500, 1500) I cannot understand it, because the ratio of they may be 6:2:2 if...
When we normalized features, it seemed that the columns were features and the rows were samples, so why not normalize the columns? Could someone give me some suggestions?
Hi,tkipf. when I use pygcn deal with citeseer dataset, there is a abnormal issue：dtype=np.int32).reshape(edges_unordered.shape)，TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'. How I...
Can this code (pygcn) be used directly in transductive learning? I notice that the train loss (in train.py) is calculated as `loss_train = F.nll_loss(output[idx_train], labels[idx_train])`, but in paper _SEMI-SUPERVISED CLASSIFICATION...
When I change the dataset to citeseer, and the result seems bad.
other scope dataset is a file (one file) and shape is below column1, column2, column3, ...column9, label 1500, 45, 1, .... 0 933, 22, 0, .... 0 1234, 30, 1,...
I try below command log-> python setup.py install running install error: can't create or remove files in install directory The following error occurred while trying to add or remove files...
Hi, I'm learning GCN and read your code, Not sure whats the use of fast mode? Seems that dropout may make the eval set accuracy inaccurate? I'm a learner so...
