shenweichen / graphneuralnetwork

Implementation and experiments of graph neural netwokrs, like gcn,graphsage,gat,etc.

graphneuralnetwork's Issues

看实现，采样部分与论文有出入？

graphsage 采样

这里的实现是分两次采样邻居，而非论文中由选定点出发采样形成子图？
请问采样部分与论文中是否有出入呢？

Is it possible to modify the model to be applicable for 3D(input has rank 3) ?

您好，如果是三维输入，是直接改模型好呢，还是用一个循环跑input.shape[0]次比较好呢？

gcn.py报错

line 49, in
batch_size=A.shape[0], epochs=NB_EPOCH, shuffle=False, verbose=2, callbacks=[mc_callback])
line 880, in fit
validation_steps=validation_steps)
line 329, in model_iteration
batch_outs = f(ins_batch)
line 3061, in call
dtype=tensor_type.as_numpy_dtype))
line 501, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.

Question about data

Hi! I'm reading this paper and try to exploit your ways to other application.
I have some questions about input data format.
1.cora.features. How did you get the eigenvector?
2.cora_edgelist.txt. What's the difference between it and cora.cites

Thanks.

gcn.py 报错。

TypeError: in converted code:

/home/jupyter-tide1994/tide/embedding/GraphNeuralNetwork-master/gnn/gcn.py:73 call *

TypeError: Input 'pred' of 'Switch' Op has type float32 that does not match expected type of bool.

def call(self, inputs, training=None, **kwargs):
    features, A = inputs
    features = self.dropout(features, training=training)
    output = tf.matmul(tf.sparse_tensor_dense_matmul(A, features), self.kernel)
    if self.bias:
        output += self.bias
    act = self.activation(output)

    act._uses_learning_phase = features._uses_learning_phase
    return act

graphsage报错

2020-02-04 16:35:37.621143: I C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
Traceback (most recent call last):
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1323, in _do_call
return fn(*args)
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1302, in _run_fn
status, run_metadata)
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InternalError: Unsupported feed type

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 889, in run
run_metadata_ptr)
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1317, in _do_run
options, run_metadata)
File "E:\Users\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Unsupported feed type

（tensorflow==1.4.0）

suggestion

python version should be included in the README.