zhouchunpong/gcn_keras

图卷积神经网络 Graph Convolutional Network with Keras

gcn_keras's Issues

训练时在跑到Epoch 12/200就停止了

setting an array element with a sequence

直接运行代码的时候，报错：setting an array element with a sequence

我的环境是：
win10
python 3.7
tensorflow 1.14.0
keras 2.3.1

另外，能否加个QQ请教一下？我的QQ是：2363405977

Got error when fitting with tensorflow2

I got the following error when running model.fit. How do I fix it?

environment: python3.7 scipy 1.4.1 tensorflow 2.1.0

Using TensorFlow backend.
Loading cora dataset...
Dataset has 2708 nodes, 5429 edges, 1433 features.
Using local pooling filters...
2020-05-05 21:10:48.564918: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-05-05 21:10:48.581495: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9c91ca7aa0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-05-05 21:10:48.581513: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
File ".../train.py", line 78, in
batch_size=A.shape[0], epochs=1, shuffle=False, verbose=0)
File "/usr/local/lib/python3.7/site-packages/keras/engine/training.py", line 1239, in fit
validation_freq=validation_freq)
File "/usr/local/lib/python3.7/site-packages/keras/engine/training_arrays.py", line 196, in fit_loop
outs = fit_function(ins_batch)
File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py", line 3727, in call
outputs = self._graph_fn(*converted_inputs)
File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1551, in call
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1591, in _call_impl
return self._call_flat(args, self.captured_inputs, cancellation_manager)
File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1692, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 527, in call
(len(args), len(list(self.signature.input_arg))))
ValueError: Arguments and signature arguments do not match. got: 21, expected: 23

ValueError: setting an array element with a sequence.

tf version: 1.14.0

Train on 2708 samples, validate on 2708 samples
Epoch 1/200
Traceback (most recent call last):
  File "D:\JetBrains\Toolbox\apps\PyCharm-P\ch-0\201.6668.115\plugins\python\helpers\pydev\pydevd.py", line 1438, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "D:\JetBrains\Toolbox\apps\PyCharm-P\ch-0\201.6668.115\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "C:/Users/PC/Desktop/GCN_Keras-master/train.py", line 85, in <module>
    callbacks=[es_callback])
  File "D:\python37\lib\site-packages\keras\engine\training.py", line 1239, in fit
    validation_freq=validation_freq)
  File "D:\python37\lib\site-packages\keras\engine\training_arrays.py", line 196, in fit_loop
    outs = fit_function(ins_batch)
  File "D:\python37\lib\site-packages\tensorflow\python\keras\backend.py", line 3277, in __call__
    dtype=tensor_type.as_numpy_dtype))
  File "D:\python37\lib\site-packages\numpy\core\_asarray.py", line 85, in asarray
    return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.

How to solve it?

MCGCN.py里preprocess_features()方法似乎没有定义或者没有声明调用的库

你好，X = preprocess_features(X)这行代码显示Unresolved reference 'preprocess_features'，似乎缺少这个模块，这个模块是在哪定义的呢？还是说这个函数就是后面一行的preprocess_adj()方法呢？

function not found

in MCGCN.py
line 25,26

A, X, y_train, y_val, y_test, train_mask, val_mask, test_mask = load_original_data( 'cora')  # {'cora', 'citeseer', 'pubmed'}
X = preprocess_features(X)

模型调用报错

运行：
predict = model.predict(X)
报错：
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 6 array(s), but instead got the following list of 1 arrays: [array([[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0....

我对图卷积神经网络挺感兴趣，能方便加个好友嘛