我正试图在this guide之后提供我的再训练初始模型（你可能也会看到this guide，它解释了如何重新开始训练）。我已修改 retrain.py 以导出我的模型，如下所示：
... # Same as in the original script:
# Set up the pre-trained graph.
maybe_download_and_extract()
graph, bottleneck_tensor, jpeg_data_tensor, resized_image_tensor = (create_inception_graph())
... # Same as in the original script:
# Add the new layer that we'll be training.
(train_step, cross_entropy, bottleneck_input, ground_truth_input, final_tensor) = add_final_training_ops(len(image_lists.keys()),
FLAGS.final_tensor_name,
bottleneck_tensor)
... # Added at the end of the original script:
# Export model
with graph.as_default():
export_path = sys.argv[-1]
print('Exporting trained model to', export_path)
saver = tf.train.Saver(sharded=True)
model_exporter = exporter.Exporter(saver)
signature = exporter.classification_signature(input_tensor=jpeg_data_tensor, scores_tensor=final_tensor)
model_exporter.init(sess.graph.as_graph_def(), default_graph_signature=signature)
model_exporter.export(export_path, tf.constant(FLAGS.export_version), sess)
print('Done exporting!')
if __name__ == '__main__':
tf.app.run()
导出我的模型后，我开始运行服务器：
/serving/bazel-bin/tensorflow_serving/example/inception_inference --port=9000 EXPORT_DIR &> inception_log &
服务器日志文件（inception_log）包含：
I tensorflow_serving/core/basic_manager.cc:190] Using InlineExecutor for BasicManager.
I tensorflow_serving/example/inception_inference.cc:384] Waiting for models to be loaded...
I tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:147] File-system polling found servable version {name: default version: 1} at path /tf_files/scope/export/00000001
I external/org_tensorflow/tensorflow/contrib/session_bundle/session_bundle.cc:129] Attempting to load a SessionBundle from: /tf_files/scope/export/00000001
I tensorflow_serving/example/inception_inference.cc:384] Waiting for models to be loaded...
I tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:147] File-system polling found servable version {name: default version: 1} at path /tf_files/scope/export/00000001
I external/org_tensorflow/tensorflow/contrib/session_bundle/session_bundle.cc:106] Running restore op for SessionBundle
I external/org_tensorflow/tensorflow/contrib/session_bundle/session_bundle.cc:203] Done loading SessionBundle
I tensorflow_serving/example/inception_inference.cc:350] Running...
I tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:147] File-system polling found servable version {name: default version: 1} at path /tf_files/scope/export/00000001
I tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:147] File-system polling found servable version {name: default version: 1} at path /tf_files/scope/export/00000001
I tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:147] File-system polling found servable version {name: default version: 1} at path /tf_files/scope/export/00000001
...
最后，我运行客户端，我收到以下错误：
/serving/bazel-bin/tensorflow_serving/example/inception_client --server=localhost:9000 --image=TEST_IMG
D0805 09:10:46.208704633 200 ev_posix.c:101] Using polling engine: poll
Traceback (most recent call last):
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tensorflow_serving/example/inception_client.py", line 53, in <module>
tf.app.run()
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/external/org_tensorflow/tensorflow/python/platform/app.py", line 30, in run
sys.exit(main(sys.argv))
File "/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tensorflow_serving/example/inception_client.py", line 48, in main
result = stub.Classify(request, 10.0) # 10 secs timeout
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 300, in __call__
self._request_serializer, self._response_deserializer)
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 198, in _blocking_unary_unary
raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.INTERNAL, details="FetchOutputs node : not found")
E0805 09:10:47.129263239 200 chttp2_transport.c:1810] close_transport: {"created":"@1470388247.129230608","description":"FD shutdown","file":"src/core/lib/iomgr/ev_poll_posix.c","file_line":427}
非常感谢任何有关此事的建议或指导。
答案 0 :(得分：1)
因此，tensorflow网站上的链接只是从我的经验中全面服务模型的一种方式。更好的服务模式的方法是从Flask和Kubernetes提供服务，因为它比所有的tensorflow服务基础设施更轻的客户端，但这是假设你的体积不是很大（ ＆gt; 100 QPS）虽然您可以使用Flask和Kubernetes提供Inception，但是按照这个速度我会选择内联解决方案。
您可以通过远程服务提供服务，这样可行，但根据您的基础设施，您可以＆＃34;可以＆＃34;还可以在流式作业中为该模型提供服务，该作业通过apache_beam.DoFn推送您的请求，然后将其输出回您的工作正在收听的MQ。这只是另一种解决方案。希望这会有所帮助。
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import logging
import tensorflow as tf
import numpy as np
import apache_beam as beam
class InferenceFn(beam.DoFn):
def __init__(self, model_dict):
super(InferenceFn, self).__init__()
self.model_dict = model_dict
self.graph = None
self.create_graph()
def create_graph(self):
if not tf.gfile.FastGFile(self.model_dict['model_full_path']):
self.download_model_file()
with tf.Graph().as_default() as graph:
with tf.gfile.FastGFile(self.model_dict['model_full_path'], 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
self.graph = graph
def start_bundle(self):
"""Prevents graph object serialization until serving. Required for GCP Serving"""
self.create_graph()
def process(self, element):
"""Core Processing Fn for Apache Beam."""
try:
with tf.Session(graph=self.graph) as sess:
if not tf.gfile.Exists(element):
tf.logging.fatal('File does not exist %s', element)
raise ReferenceError("Couldnt Find the image {}".format(element))
data = tf.gfile.FastGFile(element, 'rb').read()
output_tensor = sess.graph.get_tensor_by_name(self.model_dict['output_tensor_name'])
predictions = sess.run(softmax_tensor, {self.model_dict['input_tensor_name']: data})
predictions = np.squeeze(predictions)
yield str(predictions)
except Exception:
logging.error("We hit an error in inference on {}".format(element))