如何序列化dnnclassifier所需的张量输入(serving_input_reciever)

时间:2018-06-21 09:22:33

标签: c# python tensorflow tensorflowsharp

我希望能够使用tensorflowsharp在IIS之上使用dnnclassifier(估计器)。该模型先前已在python中进行过训练。到目前为止,我现在可以生成PB文件,知道正确的输入/输出,但是我陷入了使用字符串输入的tensorflowsharp问题。

我可以创建虹膜数据集的有效.pb文件。它使用以下feate_spec:

{'SepalLength': FixedLenFeature(shape=(1,), dtype=tf.float32, default_value=None), 'SepalWidth': FixedLenFeature(shape=(1,), dtype=tf.float32, default_value=None), 'PetalLength': FixedLenFeature(shape=(1,), dtype=tf.float32, default_value=None), 'PetalWidth': FixedLenFeature(shape=(1,), dtype=tf.float32, default_value=None)}

我创建了一个简单的c#控制台来尝试旋转它。输入应为“ input_example_tensor”,输出应位于“ dnn / head / predictions / probability”中。在alex_zu使用save_model_cli命令here提供帮助之后,我发现了这一点。

据我所知,所有tensorflow估计器API的工作都是这样的。

问题来了:input_example_tensor应该是一种字符串格式,该字符串格式将由ParseExample函数在内部进行解析。现在我被困住了。我已经找到TFTensor.CreateString,但这不能解决问题。

using System;
using TensorFlow;

namespace repository
{
    class Program
    {
        static void Main(string[] args)
        {
            using (TFGraph tfGraph = new TFGraph()){
                using (var tmpSess = new TFSession(tfGraph)){
                    using (var tfSessionOptions = new TFSessionOptions()){
                        using (var metaGraphUnused = new TFBuffer()){

                            //generating a new session based on the pb folder location with the tag serve
                            TFSession tfSession = tmpSess.FromSavedModel(
                                tfSessionOptions,
                                null,
                                @"path/to/model/pb", 
                                new[] { "serve" }, 
                                tfGraph, 
                                metaGraphUnused
                            );

                            //generating a new runner, which will fetch the tensorflow results later
                            var runner = tfSession.GetRunner();

                            //this is in the actual tensorflow documentation, how to implement this???
                            string fromTensorflowPythonExample = "{'SepalLength': [5.1, 5.9, 6.9],'SepalWidth': [3.3, 3.0, 3.1],'PetalLength': [1.7, 4.2, 5.4],'PetalWidth': [0.5, 1.5, 2.1],}";

                            //this is the problem, it's not working...
                            TFTensor rawInput = new TFTensor(new float[4]{5.1f,3.3f,1.7f,0.5f});
                            byte[] serializedTensor = System.Text.Encoding.ASCII.GetBytes(rawInput.ToString());
                            TFTensor inputTensor = TensorFlow.TFTensor.CreateString (serializedTensor);

                            runner.AddInput(tfGraph["input_example_tensor"][0], inputTensor);
                            runner.Fetch("dnn/head/predictions/probabilities", 0);

                            //start the run and get the results of the iris example
                            var output = runner.Run();
                            TFTensor result = output[0];

                            //printing response to the client
                            Console.WriteLine(result.ToString());
                            Console.ReadLine();
                        } 
                    }
                }
            }
        }
    }
}

此示例将出现以下错误:

An unhandled exception of type 'TensorFlow.TFException' occurred in TensorFlowSharp.dll: 'Expected serialized to be a vector, got shape: []
 [[Node: ParseExample/ParseExample = ParseExample[Ndense=4, Nsparse=0, Tdense=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], dense_shapes=[[1], [1], [1], [1]], sparse_types=[], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_input_example_tensor_0_0, ParseExample/ParseExample/names, ParseExample/ParseExample/dense_keys_0, ParseExample/ParseExample/dense_keys_1, ParseExample/ParseExample/dense_keys_2, ParseExample/ParseExample/dense_keys_3, ParseExample/Const, ParseExample/Const, ParseExample/Const, ParseExample/Const)]]'

如何以可以正确使用pb文件的方式序列化张量?

我还在github上发布了此问题,在这里您可以找到鸢尾花示例python文件,pb文件和控制台应用程序。我认为解决方案会产生一个  适用于所有拥有古老生产环境(如我)的tensorflow用户的灵巧解决方案。

1 个答案:

答案 0 :(得分:0)

可以通过使用Expected serialized to be a vector, got shape: []函数的重载来解决TFTensor.CreateString错误:该模型显然不希望直接获取字符串,而是期望一个包含单个字符串的向量:

TFTensor inputTensor = TFTensor.CreateString(new byte[][] { bytes }, new TFShape(1));

在您的情况下,input_example_tensor现在期望序列化的Example原始消息(另请参见the docsthe example.proto文件)。

使用protobuf编译器,我生成了一个包含Example类的C#文件。您可以从这里下载:https://pastebin.com/iLT8MUdR。具体来说,我将此online toolCSharpProtoc一起使用,并用that file中定义的消息替换了import "tensorflow/core/example/feature.proto";行。

将文件添加到项目后,您将需要引用Google.Protobuf的程序包。然后,您可以将序列化的示例传递给模型,如下所示:

Func<float, Tensorflow.Feature> makeFeature = (float x) => {
    var floatList = new Tensorflow.FloatList();
    floatList.Value.Add(x);
    return new Tensorflow.Feature { FloatList = floatList };
};

var example = new Tensorflow.Example { Features = new Tensorflow.Features() };
example.Features.Feature.Add("SepalLength", makeFeature(5.1f));
example.Features.Feature.Add("SepalWidth",  makeFeature(3.3f));
example.Features.Feature.Add("PetalLength", makeFeature(1.7f));
example.Features.Feature.Add("PetalWidth",  makeFeature(0.5f));

TFTensor inputTensor = TFTensor.CreateString(
    new [] { example.ToByteArray() }, new TFShape(1));

runner.AddInput(tfGraph["input_example_tensor"][0], inputTensor);
runner.Fetch("dnn/head/predictions/probabilities", 0);

//start the run and get the results of the iris example
var output = runner.Run();
TFTensor result = output[0];