5 out of the last 5 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing.

[CUN-bjy]

When the train.py module run, some warning happen on the tensorflow. and the speed is critically slow..

I cannot sure if it depends on GPU using or not.

WARNING:tensorflow:5 out of the last 5 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:6 out of the last 6 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:7 out of the last 7 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:8 out of the last 8 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:9 out of the last 9 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:10 out of the last 10 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:11 out of the last 11 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
WARNING:tensorflow:11 out of the last 11 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.

[CUN-bjy]

That error happen on below function, especially on self.critic.train_on_batch(obs,acts,critic_target).

def update_networks(self, obs, acts, critic_target):
    """ Train actor & critic from sampled experience
    """
    # update critic
    self.critic.train_on_batch(obs, acts, critic_target) ##########!!!

    # get next action and Q-value Gradient
    actions = self.actor.network.predict(obs)

    # update actor
    self.actor.train(obs,actions,self.critic.network)

    # update target networks
    self.actor.target_update()
    self.critic.target_update()

[CUN-bjy]

https://stackoverflow.com/questions/62398282/poor-performance-of-tensorflow-2-keras-model-with-variable-length-training-data

[CUN-bjy]

tensorflow1.x based optimizer on critic was the problem. So, I change the critic's optimizer to tf2.x-based optimizer(eager mode). And then solved.