如果您的模型是使用 Estimator.export_savedmodel() 导出的,并且您成功构建了 TensorFlow Serving 本身,您可以执行以下操作:
from grpc.beta import implementations
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2
tf.app.flags.DEFINE_string('server', 'localhost:9000', 'Server host:port.')
tf.app.flags.DEFINE_string('model', 'wide_and_deep', 'Model name.')
FLAGS = tf.app.flags.FLAGS
...
def main(_):
host, port = FLAGS.server.split(':')
# Set up a connection to the TF Model Server
channel = implementations.insecure_channel(host, int(port))
stub = prediction_service_pb2.beta_create_PredictionService_stub(channel)
# Create a request that will be sent for an inference
request = predict_pb2.PredictRequest()
request.model_spec.name = FLAGS.model
request.model_spec.signature_name = 'serving_default'
# A single tf.Example that will get serialized and turned into a TensorProto
feature_dict = {'age': _float_feature(value=25),
'capital_gain': _float_feature(value=0),
'capital_loss': _float_feature(value=0),
'education': _bytes_feature(value='11th'.encode()),
'education_num': _float_feature(value=7),
'gender': _bytes_feature(value='Male'.encode()),
'hours_per_week': _float_feature(value=40),
'native_country': _bytes_feature(value='United-States'.encode()),
'occupation': _bytes_feature(value='Machine-op-inspct'.encode()),
'relationship': _bytes_feature(value='Own-child'.encode()),
'workclass': _bytes_feature(value='Private'.encode())}
label = 0
example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
serialized = example.SerializeToString()
request.inputs['inputs'].CopyFrom(
tf.contrib.util.make_tensor_proto(serialized, shape=[1]))
# Create a future result, and set 5 seconds timeout
result_future = stub.Predict.future(request, 5.0)
prediction = result_future.result().outputs['scores']
print('True label: ' + str(label))
print('Prediction: ' + str(np.argmax(prediction)))
这里我写了一个简单的教程Exporting and Serving a TensorFlow Wide & Deep Model 有更多的细节。
希望对你有帮助。