heaphop30 / graph-attention-nets Goto Github PK

Hello Sir,
I was using your code of MoNet on custom demo dataset and faced following error:
please help me in removing it.
Layer 0: M_0 = |V| = 976 nodes (192 added), |E| = 3198 edges
Layer 1: M_1 = |V| = 488 nodes (79 added), |E| = 1448 edges
Layer 2: M_2 = |V| = 244 nodes (27 added), |E| = 687 edges
Layer 3: M_3 = |V| = 122 nodes (5 added), |E| = 343 edges
Layer 4: M_4 = |V| = 61 nodes (0 added), |E| = 160 edges
(32, 976, 1)
Traceback (most recent call last):

File "", line 1, in
runfile('E:/MOdels_for_multilabel/graph-attention-nets-master/core/MoNet_chest.py', wdir='E:/MOdels_for_multilabel/graph-attention-nets-master/core')

File "C:\Users\dell\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 704, in runfile
execfile(filename, namespace)

File "C:\Users\dell\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "E:/MOdels_for_multilabel/graph-attention-nets-master/core/MoNet_chest.py", line 895, in
model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=epochs)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py", line 108, in _method_wrapper
return method(self, *args, **kwargs)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1098, in fit
tmp_logs = train_function(iterator)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py", line 780, in call
result = self._call(*args, **kwds)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py", line 823, in _call
self._initialize(args, kwds, add_initializers_to=initializers)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py", line 697, in _initialize
*args, **kwds))

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py", line 2855, in _get_concrete_function_internal_garbage_collected
graph_function, _, _ = self._maybe_define_function(args, kwargs)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py", line 3213, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py", line 3075, in _create_graph_function
capture_by_value=self._capture_by_value),

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py", line 986, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py", line 600, in wrapped_fn
return weak_wrapped_fn().wrapped(*args, **kwds)

File "C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py", line 973, in wrapper
raise e.ag_error_metadata.to_exception(e)

ValueError: in user code:

C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
    return step_function(self, iterator)
E:/MOdels_for_multilabel/graph-attention-nets-master/core/MoNet_chest.py:836 call  *
    weighting = self.weightings[k](X)
E:/MOdels_for_multilabel/graph-attention-nets-master/core/MoNet_chest.py:797 call  *
    X_t = tf.reshape(tf.transpose(X, [1,2,0]), [n_nodes, batch_size * n_features])
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper  **
    return target(*args, **kwargs)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py:195 reshape
    result = gen_array_ops.reshape(tensor, shape, name)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py:8234 reshape
    "Reshape", tensor=tensor, shape=shape, name=name)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:744 _apply_op_helper
    attrs=attr_protos, op_def=op_def)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py:593 _create_op_internal
    compute_device)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:3485 _create_op_internal
    op_def=op_def)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1975 __init__
    control_input_ops, op_def)
C:\Users\dell\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py:1815 _create_c_op
    raise ValueError(str(e))

ValueError: Cannot reshape a tensor with 31232 elements to shape [976,1] (976 elements) for '{{node sequential/mo_net/weighting/Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32](sequential/mo_net/weighting/transpose, sequential/mo_net/weighting/Reshape/shape)' with input shapes: [976,1,32], [2] and with input tensors computed as partial shapes: input[1] = [976,1].

core.zip

In the class Attention in gat.ipynb, the shape of self.W is (F_1,F), I think that F_1 is the output_dim, so the shape should be (F,F_1). Is this right?