【发布时间】:2017-07-27 23:46:05
【问题描述】:
我正在使用 Tensorflow 对象检测 API (github.com/tensorflow/models/tree/master/object_detection) 执行一项对象检测任务。现在,我在为使用 Tensorflow Serving(tensorflow.github.io/serving/) 训练的检测模型提供服务时遇到问题。
1. 我遇到的第一个问题是将模型导出到可服务文件。 对象检测 api 包含导出脚本,以便我能够将 ckpt 文件转换为带有变量的 pb 文件。但是,输出文件在“变量”文件夹中不会有任何内容。我虽然这是一个错误并在 Github 上报告了它,但似乎他们实习将变量转换为常量,这样就不会有变量了。详情可见HERE。
我在导出保存的模型时使用的标志如下:
CUDA_VISIBLE_DEVICES=0 python export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path configs/rfcn_resnet50_car_Jul_20.config \
--checkpoint_path resnet_ckpt/model.ckpt-17586 \
--inference_graph_path serving_model/1 \
--export_as_saved_model True
当我将 --export_as_saved_model 切换为 False 时,它在 python 中运行得非常好。
但是,我仍然无法为模型提供服务。
当我试图跑步时:
~/serving$ bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=gan --model_base_path=<my_model_path>
我明白了:
2017-07-27 16:11:53.222439: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:155] Restoring SavedModel bundle.
2017-07-27 16:11:53.222497: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:165] The specified SavedModel has no variables; no checkpoints were restored.
2017-07-27 16:11:53.222502: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:190] Running LegacyInitOp on SavedModel bundle.
2017-07-27 16:11:53.229463: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:284] Loading SavedModel: success. Took 281805 microseconds.
2017-07-27 16:11:53.229508: I tensorflow_serving/core/loader_harness.cc:86] Successfully loaded servable version {name: gan version: 1}
2017-07-27 16:11:53.244716: I tensorflow_serving/model_servers/main.cc:290] Running ModelServer at 0.0.0.0:9000 ...
我认为模型没有正确加载,因为它显示“指定的 SavedModel 没有变量;没有恢复检查点。”
但是既然我们已经把所有的变量都转换成了常量,这似乎是合理的。我不确定这里。
2。我无法使用客户端调用服务器并对示例图像进行检测。
客户端脚本如下:
from __future__ import print_function
from __future__ import absolute_import
# Communication to TensorFlow server via gRPC
from grpc.beta import implementations
import tensorflow as tf
import numpy as np
from PIL import Image
# TensorFlow serving stuff to send messages
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2
# Command line arguments
tf.app.flags.DEFINE_string('server', 'localhost:9000',
'PredictionService host:port')
tf.app.flags.DEFINE_string('image', '', 'path to image in JPEG format')
FLAGS = tf.app.flags.FLAGS
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
def main(_):
host, port = FLAGS.server.split(':')
channel = implementations.insecure_channel(host, int(port))
stub = prediction_service_pb2.beta_create_PredictionService_stub(channel)
# Send request
request = predict_pb2.PredictRequest()
image = Image.open(FLAGS.image)
image_np = load_image_into_numpy_array(image)
image_np_expanded = np.expand_dims(image_np, axis=0)
# Call GAN model to make prediction on the image
request.model_spec.name = 'gan'
request.model_spec.signature_name = 'predict_images'
request.inputs['inputs'].CopyFrom(
tf.contrib.util.make_tensor_proto(image_np_expanded))
result = stub.Predict(request, 60.0) # 60 secs timeout
print(result)
if __name__ == '__main__':
tf.app.run()
为了匹配request.model_spec.signature_name = 'predict_images',我从第 289 行开始修改了对象检测 api (github.com/tensorflow/models/blob/master/object_detection/exporter.py) 中的 exporter.py 脚本:
signature_def_map={
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
detection_signature,
},
收件人:
signature_def_map={
'predict_images': detection_signature,
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
detection_signature,
},
因为我不知道如何调用默认签名密钥。
当我运行以下命令时:
bazel-bin/tensorflow_serving/example/client --server=localhost:9000 --image=<my_image_file>
我收到以下错误消息:
Traceback (most recent call last):
File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/tf_serving/tensorflow_serving/example/client.py", line 54, in <module>
tf.app.run()
File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/tf_serving/tensorflow_serving/example/client.py", line 49, in main
result = stub.Predict(request, 60.0) # 60 secs timeout
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 324, in __call__
self._request_serializer, self._response_deserializer)
File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 210, in _blocking_unary_unary
raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.NOT_FOUND, details="FeedInputs: unable to find feed output ToFloat:0")
不太清楚这里发生了什么。
最初我虽然可能我的客户端脚本不正确,但在我发现 AbortionError 来自 github.com/tensorflow/tensorflow/blob/f488419cd6d9256b25ba25cbe736097dfeee79f9/tensorflow/core/graph/subgraph.cc 之后。似乎我在构建图表时遇到了这个错误。所以这可能是我遇到的第一个问题造成的。
我对这个东西很陌生,所以我真的很困惑。我想我可能一开始就错了。有什么方法可以正确导出和服务检测模型?任何建议都会有很大帮助!
【问题讨论】:
-
我收到
code=StatusCode.FAILED_PRECONDITION, details="Serving signature key "predict_images" not found."。不过,我根据您的代码更新了 exporter.py 文件。有什么想法吗? -
@PamioSolanky 你可以看到exporter.py 276-277行的原始代码,我做了一些修改。而是使用 signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY 作为服务签名密钥,我将其更改为“predict_images”。所以我可以使用上面发布的客户端代码来调用它。如果您没有更改它,您可能会使用默认服务签名密钥,或者通过将其添加到您的标志来分配您自己的密钥。
标签: tensorflow object-detection tensorflow-serving