Type Error when using AttentionLayer()

[Ichraknaceur]

i got this error :

TypeError Traceback (most recent call last) in ----> 1 attn_op, attn_state = attn_layer([encoder_outputs, output]) 2 decoder_concat_input = Concatenate(axis=-1)([output, attn_op])

5 frames /usr/local/lib/python3.7/dist-packages/keras/engine/keras_tensor.py in array(self, dtype) 253 def array(self, dtype=None): 254 raise TypeError( --> 255 f'You are passing {self}, an intermediate Keras symbolic input/output, ' 256 'to a TF API that does not allow registering custom dispatchers, such ' 257 'as tf.cond, tf.function, gradient tapes, or tf.map_fn. '

TypeError: Exception encountered when calling layer "tf.keras.backend.rnn_6" (type TFOpLambda).

You are passing KerasTensor(type_spec=TensorSpec(shape=(None, 13), dtype=tf.float32, name=None), name='tf.compat.v1.nn.softmax_13/Softmax:0', description="created by layer 'tf.compat.v1.nn.softmax_13'"), an intermediate Keras symbolic input/output, to a TF API that does not allow registering custom dispatchers, such as tf.cond, tf.function, gradient tapes, or tf.map_fn. Keras Functional model construction only supports TF API calls that do support dispatching, such as tf.math.add or tf.reshape. Other APIs cannot be called directly on symbolic Kerasinputs/outputs. You can work around this limitation by putting the operation in a custom Keras layer call and calling that layer on this symbolic input/output.

Call arguments received by layer "tf.keras.backend.rnn_6" (type TFOpLambda): • step_function=<function AttentionLayer.call..energy_step at 0x7fdf2baa4440> • inputs=tf.Tensor(shape=(None, 13, 800), dtype=float32) • initial_states=['tf.Tensor(shape=(None, 13), dtype=float32)'] • go_backwards=False • mask=None • constants=None • unroll=False • input_length=None • time_major=False • zero_output_for_mask=False