Export a model
# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
feature_spec = tf.feature_column.make_parse_example_spec(my_feature_columns)
serving_input_receiver_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)
export_dir = classifier.export_savedmodel('export', serving_input_receiver_fn)
or
def serving_input_receiver_fn():
max_seq_length = FLAGS.max_seq_length
batch_size = 1
feature_spec = {
"unique_ids": tf.FixedLenFeature([], tf.int64),
"input_ids": tf.FixedLenFeature([max_seq_length], tf.int64),
"input_mask": tf.FixedLenFeature([max_seq_length], tf.int64),
"segment_ids": tf.FixedLenFeature([max_seq_length], tf.int64),
}
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[batch_size],
name='input_example_tensor')
receiver_tensors = {'examples': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
..
..
estimator.export_saved_model(
export_dir_base=EXPORT_PATH,
serving_input_receiver_fn=serving_input_receiver_fn)
saved_model_cli 를 이용해 모델의 입/출력을 확인하자.
$ saved_model_cli show --dir export/1568007663 --tag_set serve --signature_def serving_default
The given SavedModel SignatureDef contains the following input(s):
inputs['inputs'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: input_example_tensor:0
The given SavedModel SignatureDef contains the following output(s):
outputs['classes'] tensor_info:
dtype: DT_STRING
shape: (-1, 3)
name: dnn/head/Tile:0
outputs['scores'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 3)
name: dnn/head/predictions/probabilities:0
Method name is: tensorflow/serving/classify
Serve TensforFlow Estimator with SavedModel
http://shzhangji.com/blog/2018/05/14/serve-tensorflow-estimator-with-savedmodel/How to export tf.learn.DNNClassifier model for serving? #488
https://github.com/tensorflow/tensorflow/issues/12508#issuecomment-325422910
How to run it as a server
$ tensorflow_model_server --rest_api_port=8501 --model_name=iris --model_base_path=/home/hm_home/work/anything/ml/iris/export
- 8500: gRPC
- 8501: rest api
How to test it as a client
/tmp/temp.json
[{"SepalLength":[5.1],"SepalWidth":[3.3],"PetalLength":[1.7],"PetalWidth":[0.5]}]
$ curl -X POST http://localhost:8501/v1/models/iris:classify -H "Content-Type: application/json" -d @/tmp/temp.json
반응형
'Develop' 카테고리의 다른 글
개발과정에서 자주 사용하는 명령어 모음 (0) | 2019.09.15 |
---|---|
불필요한 브렌치 자동 제거 스트립트 (0) | 2019.09.13 |
힐월드 개발 구성 환경 (0) | 2017.02.09 |
Healworld - 2017. 2. 4(토) - 기능 정리 (0) | 2017.02.04 |
Healworld - 2017. 1. 31(화) (0) | 2017.01.31 |