python - 如何使用 export_savedmodel 函数导出 Estimator 模型

Question

有没有关于 export_savedmodel 的教程？

我已经经历了this article在 tensorflow.org 和 unittest code在github.com上，仍然不知道如何构造函数export_savedmodel

的参数 serving_input_fn

Answer 1

这样做:

your_feature_spec = {
    "some_feature": tf.FixedLenFeature([], dtype=tf.string, default_value=""),
    "some_feature": tf.VarLenFeature(dtype=tf.string),
}

def _serving_input_receiver_fn():
    serialized_tf_example = tf.placeholder(dtype=tf.string, shape=None, 
                                           name='input_example_tensor')
    # key (e.g. 'examples') should be same with the inputKey when you 
    # buid the request for prediction
    receiver_tensors = {'examples': serialized_tf_example}
    features = tf.parse_example(serialized_tf_example, your_feature_spec)
    return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

estimator.export_savedmodel(export_dir, _serving_input_receiver_fn)

然后可以批量请求带有“预测”签名名称的服务模型。

来源:https://www.tensorflow.org/guide/saved_model#prepare_serving_inputs