将经过重新训练的初始SavedModel部署到Google Cloud ml引擎 [英] Deploy retrained inception SavedModel to google cloud ml engine

问题描述

我正在尝试在Google Cloud ml-engine上部署初始模型的经过重新训练的版本.从 SavedModel文档收集信息参考，以及此

I am trying to deploy a retrained version of the inception model on google cloud ml-engine. Gathering informations from the SavedModel documentation, this reference, and this post of rhaertel80, I exported successfully my retrained model to a SavedModel, uploaded it to a bucket and tried to deploy it to a ml-engine version.

最后一个任务实际上创建了一个版本，但输出了此错误:

This last task actually creates a version, but it outputs this error:

Create Version failed. Bad model detected with error: "Error loading the model: Unexpected error when loading the model"

当我尝试通过命令行从模型中获取预测时，出现以下错误消息: "message": "Field: name Error: Online prediction is unavailable for this version. Please verify that CreateVersion has completed successfully."

And when I try to get predictions from the model via commandline I get this error message: "message": "Field: name Error: Online prediction is unavailable for this version. Please verify that CreateVersion has completed successfully."

我做了几次尝试，尝试使用不同的method_name和tag选项，但是没有用.

I have made several attempts, trying different method_name and tag options but none worked.

添加到原始初始代码中的代码是

The code added to the original inception code is

  ### DEFINE SAVED MODEL SIGNATURE

  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': 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'
  )


  ### SAVE OUT THE MODEL

  b = saved_model_builder.SavedModelBuilder('new_export_dir')
  b.add_meta_graph_and_variables(sess,
                                 [tf.saved_model.tag_constants.SERVING],
                                 signature_def_map={'predict_images': signature})
  b.save() 

可能会有所帮助的其他考虑因素: 我已经使用导出的trained_graph.pb和graph_def.SerializeToString()在本地获取了预测，并且效果很好，但是当我用saved_model.pb替换它时，它就会失败.

Another consideration that might help: I have used an exported a trained_graph.pb with graph_def.SerializeToString() to get the predictions locally and it works fine, but when I substitute it with the saved_model.pb it fails.

关于问题可能有什么建议?

Any suggestions on what the issue might be?

推荐答案

在您的signature_def_map中，使用键"serving_default"，该键在

In your signature_def_map, use the key 'serving_default', which is defined in signature_constants as DEFAULT_SERVING_SIGNATURE_DEF_KEY:

b.add_meta_graph_and_variables(sess,
                               [tf.saved_model.tag_constants.SERVING],
                               signature_def_map={'serving_default': signature})

这篇关于将经过重新训练的初始SavedModel部署到Google Cloud ml引擎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IT屋！