ValueError: A KerasTensor cannot be used as input to a TensorFlow function.

[YasamanSamadi]

Hi there,
I am studetn and am trying to run the code but haven't been able.
I migrated the code to T2 but still facing this issue and am not sure how to solve it, do you have any suggestion how I can fix this
Many thanks

My issue:
when I run the code I get this error :

 File "/home/ubuntu/ComGA-master/run.py", line 107, in <module>
    runner.erun(writer)
  File "/home/ubuntu/ComGA-master/anomaly_detection.py", line 68, in erun
    model = GCNModelAE(placeholders,num_features,num_nodes,adj,features_nonzero,2000,500,128,256,128,self.at)
  File "/home/ubuntu/ComGA-master/model.py", line 64, in __init__
    self.build()
  File "/home/ubuntu/ComGA-master/model.py", line 35, in build
    self._build()
  File "/home/ubuntu/ComGA-master/model.py", line 67, in _build
    self.hidden1 =Dense(input_dim=self.n_samples,
  File "/home/ubuntu/ComGA-master/layers.py", line 70, in __call__
    outputs = self._call(inputs)
  File "/home/ubuntu/ComGA-master/layers.py", line 179, in _call
    output = tf.matmul(x, self.vars['weights'])
  File "/opt/conda/lib/python3.10/site-packages/tensorflow/python/ops/weak_tensor_ops.py", line 142, in wrapper
    return op(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/opt/conda/lib/python3.10/site-packages/keras/src/backend/common/keras_tensor.py", line 91, in __tf_tensor__
    raise ValueError(
ValueError: A KerasTensor cannot be used as input to a TensorFlow function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces `keras.layers` and `keras.operations`). You are likely doing something like:

x = Input(...)
...
tf_fn(x) # Invalid.

What you should do instead is wrap `tf_fn` in a layer:

class MyLayer(Layer):
def call(self, x):
return tf_fn(x)

x = MyLayer()(x)