YoutubeDNN example run failed

[tom729]

output: Input In [12], in 77 if tf.version >= '2.0.0': 78 tf.compat.v1.disable_eager_execution() ---> 82 model = YoutubeDNN(user_feature_columns, item_feature_columns, num_sampled=5, user_dnn_hidden_units=(64, embedding_dim)) 83 #model = MIND(user_feature_columns,item_feature_columns,dynamic_k=False,p=1,k_max=2,num_sampled=5,user_dnn_hidden_units=(64, embedding_dim)) 85 model.compile(optimizer="adam", loss=sampledsoftmaxloss) # "binary_crossentropy")

File ~/miniforge3/lib/python3.9/site-packages/deepmatch/models/youtubednn.py:56, in YoutubeDNN(user_feature_columns, item_feature_columns, num_sampled, user_dnn_hidden_units, dnn_activation, dnn_use_bn, l2_reg_dnn, l2_reg_embedding, dnn_dropout, output_activation, seed) 54 item_features = build_input_features(item_feature_columns) 55 item_inputs_list = list(item_features.values()) ---> 56 user_dnn_out = DNN(user_dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout, 57 dnn_use_bn, output_activation=output_activation, seed=seed)(user_dnn_input) 59 item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(item_features[item_feature_name]) 61 item_embedding_matrix = embedding_matrix_dict[ 62 item_feature_name]

File ~/miniforge3/lib/python3.9/site-packages/tensorflow/python/keras/engine/base_layer_v1.py:784, in Layer.call(self, *args, **kwargs) 781 try: 782 with autocast_variable.enable_auto_cast_variables( 783 self._compute_dtype_object): --> 784 outputs = call_fn(cast_inputs, *args, **kwargs) 786 except errors.OperatorNotAllowedInGraphError as e: 787 raise TypeError('You are attempting to use Python control ' 788 'flow in a layer that was not declared to be ' 789 'dynamic. Pass dynamic=True to the class ' 790 'constructor.\nEncountered error:\n"""\n' + 791 str(e) + '\n"""')

File ~/miniforge3/lib/python3.9/site-packages/tensorflow/python/autograph/impl/api.py:692, in convert..decorator..wrapper(*args, **kwargs) 690 except Exception as e: # pylint:disable=broad-except 691 if hasattr(e, 'ag_error_metadata'): --> 692 raise e.ag_error_metadata.to_exception(e) 693 else: 694 raise

FailedPreconditionError: in user code:

File "/Users/tangzhenhua/miniforge3/lib/python3.9/site-packages/deepctr/layers/core.py", line 190, in call  *
    fc = self.activation_layers[i](fc, training=training)
File "/Users/tangzhenhua/miniforge3/lib/python3.9/site-packages/keras/engine/base_layer_v1.py", line 732, in __call__  **
    base_layer_utils.create_keras_history(inputs)
File "/Users/tangzhenhua/miniforge3/lib/python3.9/site-packages/keras/engine/base_layer_utils.py", line 175, in create_keras_history
    _, created_layers = _create_keras_history_helper(tensors, set(), [])
File "/Users/tangzhenhua/miniforge3/lib/python3.9/site-packages/keras/engine/base_layer_utils.py", line 251, in _create_keras_history_helper
    constants[i] = backend.function([], op_input)([])
File "/Users/tangzhenhua/miniforge3/lib/python3.9/site-packages/keras/backend.py", line 4275, in __call__
    fetched = self._callable_fn(*array_vals,

FailedPreconditionError: 2 root error(s) found.
  (0) FAILED_PRECONDITION: Could not find variable dnn_4/bias0. This could mean that the variable has been deleted. In TF1, it can also mean the variable is uninitialized. Debug info: container=localhost, status error message=Container localhost does not exist. (Could not find resource: localhost/dnn_4/bias0)
	 [[{{node dnn_4/BiasAdd/ReadVariableOp}}]]
	 [[dnn_4/BiasAdd/ReadVariableOp/_9]]
  (1) FAILED_PRECONDITION: Could not find variable dnn_4/bias0. This could mean that the variable has been deleted. In TF1, it can also mean the variable is uninitialized. Debug info: container=localhost, status error message=Container localhost does not exist. (Could not find resource: localhost/dnn_4/bias0)
	 [[{{node dnn_4/BiasAdd/ReadVariableOp}}]]
0 successful operations.
0 derived errors ignored.

Operating environment(运行环境):

• python version 3.9
• tensorflow version 2.8
• deepmatch version 0.2.0
• OS: mac Monterey 12.1
• CPU: M1 pro