Question

我已经成功培训，导出和上传了我的“再培训_图片”。到ML引擎。我的导出脚本如下：

import tensorflow as tf
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.saved_model import builder as saved_model_builder

input_graph = 'retrained_graph.pb'
saved_model_dir = 'my_model'

with tf.Graph().as_default() as graph:
  # Read in the export graph
  with tf.gfile.FastGFile(input_graph, 'rb') as f:
      graph_def = tf.GraphDef()
      graph_def.ParseFromString(f.read())
      tf.import_graph_def(graph_def, name='')

  # Define SavedModel Signature (inputs and outputs)
  in_image = graph.get_tensor_by_name('DecodeJpeg/contents:0')
  inputs = {'image_bytes': tf.saved_model.utils.build_tensor_info(in_image)}

  out_classes = graph.get_tensor_by_name('final_result:0')
  outputs = {'prediction_bytes': tf.saved_model.utils.build_tensor_info(out_classes)}

  signature = tf.saved_model.signature_def_utils.build_signature_def(
      inputs=inputs,
      outputs=outputs,
      method_name='tensorflow/serving/predict'
  )

  with tf.Session(graph=graph) as sess:
    # Save out the SavedModel.
    b = saved_model_builder.SavedModelBuilder(saved_model_dir)
    b.add_meta_graph_and_variables(sess,
                               [tf.saved_model.tag_constants.SERVING],
                               signature_def_map={'serving_default': signature})
    b.save()

我使用以下内容构建我的预测Json：

# Copy the image to local disk.
gsutil cp gs://cloud-ml-data/img/flower_photos/tulips/4520577328_a94c11e806_n.jpg flower.jpg

# Create request message in json format.
python -c 'import base64, sys, json; img = base64.b64encode(open(sys.argv[1], "rb").read()); print json.dumps({"image_bytes": {"b64": img}}) ' flower.jpg &> request.json

# Call prediction service API to get classifications
gcloud ml-engine predict --model ${MODEL_NAME} --json-instances request.json

然而，响应失败了：

{
  "error": "Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details=\"contents must be scalar, got shape [1]\n\t [[Node: Deco
deJpeg = DecodeJpeg[_output_shapes=[[?,?,3]], acceptable_fraction=1, channels=3, dct_method=\"\", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device=\"/job:l
ocalhost/replica:0/task:0/device:CPU:0\"](_arg_DecodeJpeg/contents_0_0)]]\")"
}

任何帮助表示感谢，我能够如此接近我的品尝：D

Answer 1

服务器将解码并批处理所有输入。因此，图表的输入实际上是[base64_decode（“xxx”）]，其中您实际上想要提供base64_decode（“xxx”），因为op采用字符串类型张量。服务器端将输入的形状假定为[None，]，即第一个维度可以是用于批处理的任何内容。在你的情况下，[无]。您可能想要创建该形状的张量，然后将其提供给操作。

Answer 2

为什么你有这行in_image = graph.get_tensor_by_name（'DecodeJpeg / contents：0'）？

inputs = {'image_bytes'：tf.saved_model.utils.build_tensor_info（in_image）}这里的形状是标量。你能确保创建形状[无]

的输入

https://github.com/GoogleCloudPlatform/cloudml-samples/blob/master/flowers/trainer/model.py#L364

预测失败：内容必须是标量

2 个答案: