预测失败：内容必须是标量

问题描述

我已成功培训，导出并将我的'retrained_graph.pb'上传到ML引擎。我的导出脚本如下：

 从tensorflow.python.saved_model导入tensorflow作为tf 
导入signature_constants 
从tensorflow.python.saved_model导入tag_constants $ b $从tensorflow.python.saved_model导入生成器作为saved_model_builder 
 
 input_graph ='retrained_graph.pb'
 saved_model_dir ='my_model'
 
 with tf.Graph（）。as_default（）as graph：
＃在输出图
中读入tf.gfile.FastGFile（input_graph，'rb'）as f：
 graph_def = tf.GraphDef（）
 graph_def.ParseFromString（f.read（））
 tf.import_graph_def（graph_def，name =''）
 
＃定义SavedModel签名（输入和输出）
 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）} 
 
签名= tf.saved_model.signature_def_utils.build_signature_def（
输入=输入，
输出=输出，
 method_name = 'tensorflow / serving / predict'
）
 
 with tf.Session（graph = graph）as sess：
＃保存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（）
  

我使用以下方法构建我的预测Json：

 ＃将图像复制到本地磁盘。 
 gsutil cp gs：//cloud-ml-data/img/flower_photos/tulips/4520577328_a94c11e806_n.jpg flower.jpg 
 
＃以json格式创建请求消息。 
 python -c'import base64，sys，json; img = base64.b64encode（open（sys.argv [1]，rb）。read（））;打印json.dumps（{image_bytes：{b64：img}}）'flower.jpg&> request.json 
 
＃调用预测服务API获取分类
 gcloud ml-engine predict --model $ {MODEL_NAME} --json-instances request.json 
  

然而，这会失败并返回：

 error：预测失败：模型执行期间出错：AbortionError（code = StatusCode.INVALID_ARGUMENT，details = \内容必须是标量，变形[1] \\\
\t [[节点：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）]] \）
 
 $ / code> 

任何帮助表示感谢，我如此接近我可以品尝它：D

解决方案

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


inputs = {'image_bytes'：tf.saved_model.utils.build_tensor_info（in_image）}这里的形状是标量。你可以确保你创建形状输入[无]

I have successfully trained, exported and uploaded my 'retrained_graph.pb' to ML Engine. My export script is as follows:

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()

I build my prediction Json using the following:

# 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

However this fails with the response:

{
  "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)]]\")"
}

Any help appreciated, I'm so close I can taste it :D

解决方案

Why do you have this line in_image = graph.get_tensor_by_name('DecodeJpeg/contents:0')?

inputs = {'image_bytes': tf.saved_model.utils.build_tensor_info(in_image)} The shape here is scalar. Can you make sure you create input with shape [None]

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

这篇关于预测失败：内容必须是标量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！