How can I export the model as serving format?

[tcclks]

To export estimator m there are four steps:
1.Define estimator's features.

2.Create a feature config.

3.Build an export_input_fn suitable for use in serving.

4.Export the model using export_savedmodel().

I try to use ：
export_dir_base = "./serving_save_model"
feature_spec = {
'times': tf.placeholder(tf.float32, name='times')
}
serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)

estimator.export_savedmodel(export_dir_base, serving_input_fn)
But I encountered an error like this:

Traceback (most recent call last):
File "E:/MyProject/Py/tensorFlow_time_series_predict/train_lstm_multivariate.py", line 231, in
estimator.export_savedmodel(export_dir_base, serving_input_fn)
File "H:\ProgramFiles\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\estimator\estimator.py", line 504, in export_savedmodel
serving_input_receiver = serving_input_receiver_fn()
File "H:\ProgramFiles\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\estimator\export\export.py", line 142, in serving_input_receiver_fn
features = parsing_ops.parse_example(serialized_tf_example, feature_spec)
File "H:\ProgramFiles\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\parsing_ops.py", line 577, in parse_example
[VarLenFeature, SparseFeature, FixedLenFeature, FixedLenSequenceFeature])
File "H:\ProgramFiles\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\parsing_ops.py", line 291, in _features_to_raw_params
raise ValueError("Invalid feature %s:%s." % (key, feature))
ValueError: Invalid feature times:Tensor("times:0", dtype=float32).

How should I use it correctly?
Thanks so much！