文章内容

2017/5/28 17:17:37,作 者: 黄兵

TensorFlowSharp入门使用C#编写TensorFlow人工智能应用Ⅱ

TensorFlow C# image recognition

图像识别示例体验

https://github.com/migueldeicaza/TensorFlowSharp/tree/master/Examples/ExampleInceptionInference

下面学习一个实际的人工智能应用,是非常简单的一个示例,图像识别。

新建一个 imagerecognition .NET Framework 控制台应用项目,接着添加TensorFlowSharp 引用。

然后在项目属性中生成->平台目标 改为 x64

接着编写如下代码:

class Program
    {
        static string dir, modelFile, labelsFile;
        public static void Main(string[] args)
        {
            dir = "tmp";
            List<string> files = Directory.GetFiles("img").ToList();
            ModelFiles(dir);
            var graph = new TFGraph();
            // 从文件加载序列化的GraphDef
            var model = File.ReadAllBytes(modelFile);
            //导入GraphDef
            graph.Import(model, "");
            using (var session = new TFSession(graph))
            {
                var labels = File.ReadAllLines(labelsFile);
                Console.WriteLine("TensorFlow图像识别 LineZero");
                foreach (var file in files)
                {
                    // Run inference on the image files
                    // For multiple images, session.Run() can be called in a loop (and
                    // concurrently). Alternatively, images can be batched since the model
                    // accepts batches of image data as input.
                    var tensor = CreateTensorFromImageFile(file);

                    var runner = session.GetRunner();
                    runner.AddInput(graph["input"][0], tensor).Fetch(graph["output"][0]);
                    var output = runner.Run();
                    // output[0].Value() is a vector containing probabilities of
                    // labels for each image in the "batch". The batch size was 1.
                    // Find the most probably label index.

                    var result = output[0];
                    var rshape = result.Shape;
                    if (result.NumDims != 2 || rshape[0] != 1)
                    {
                        var shape = "";
                        foreach (var d in rshape)
                        {
                            shape += $"{d} ";
                        }
                        shape = shape.Trim();
                        Console.WriteLine($"Error: expected to produce a [1 N] shaped tensor where N is the number of labels, instead it produced one with shape [{shape}]");
                        Environment.Exit(1);
                    }

                    // You can get the data in two ways, as a multi-dimensional array, or arrays of arrays, 
                    // code can be nicer to read with one or the other, pick it based on how you want to process
                    // it
                    bool jagged = true;

                    var bestIdx = 0;
                    float p = 0, best = 0;

                    if (jagged)
                    {
                        var probabilities = ((float[][])result.GetValue(jagged: true))[0];
                        for (int i = 0; i < probabilities.Length; i++)
                        {
                            if (probabilities[i] > best)
                            {
                                bestIdx = i;
                                best = probabilities[i];
                            }
                        }

                    }
                    else
                    {
                        var val = (float[,])result.GetValue(jagged: false);

                        // Result is [1,N], flatten array
                        for (int i = 0; i < val.GetLength(1); i++)
                        {
                            if (val[0, i] > best)
                            {
                                bestIdx = i;
                                best = val[0, i];
                            }
                        }
                    }

                    Console.WriteLine($"{Path.GetFileName(file)} 最佳匹配: [{bestIdx}] {best * 100.0}% 标识为:{labels[bestIdx]}");
                }
            }
            Console.ReadKey();
        }

        // Convert the image in filename to a Tensor suitable as input to the Inception model.
        static TFTensor CreateTensorFromImageFile(string file)
        {
            var contents = File.ReadAllBytes(file);

            // DecodeJpeg uses a scalar String-valued tensor as input.
            var tensor = TFTensor.CreateString(contents);

            TFGraph graph;
            TFOutput input, output;

            // Construct a graph to normalize the image
            ConstructGraphToNormalizeImage(out graph, out input, out output);

            // Execute that graph to normalize this one image
            using (var session = new TFSession(graph))
            {
                var normalized = session.Run(
                         inputs: new[] { input },
                         inputValues: new[] { tensor },
                         outputs: new[] { output });

                return normalized[0];
            }
        }

        // The inception model takes as input the image described by a Tensor in a very
        // specific normalized format (a particular image size, shape of the input tensor,
        // normalized pixel values etc.).
        //
        // This function constructs a graph of TensorFlow operations which takes as
        // input a JPEG-encoded string and returns a tensor suitable as input to the
        // inception model.
        static void ConstructGraphToNormalizeImage(out TFGraph graph, out TFOutput input, out TFOutput output)
        {
            // Some constants specific to the pre-trained model at:
            // https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip
            //
            // - The model was trained after with images scaled to 224x224 pixels.
            // - The colors, represented as R, G, B in 1-byte each were converted to
            //   float using (value - Mean)/Scale.

            const int W = 224;
            const int H = 224;
            const float Mean = 117;
            const float Scale = 1;

            graph = new TFGraph();
            input = graph.Placeholder(TFDataType.String);

            output = graph.Div(
                x: graph.Sub(
                    x: graph.ResizeBilinear(
                        images: graph.ExpandDims(
                            input: graph.Cast(
                                graph.DecodeJpeg(contents: input, channels: 3), DstT: TFDataType.Float),
                            dim: graph.Const(0, "make_batch")),
                        size: graph.Const(new int[] { W, H }, "size")),
                    y: graph.Const(Mean, "mean")),
                y: graph.Const(Scale, "scale"));
        }

        /// <summary>
        /// 下载初始Graph和标签
        /// </summary>
        /// <param name="dir"></param>
        static void ModelFiles(string dir)
        {
            string url = "https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip";

            modelFile = Path.Combine(dir, "tensorflow_inception_graph.pb");
            labelsFile = Path.Combine(dir, "imagenet_comp_graph_label_strings.txt");
            var zipfile = Path.Combine(dir, "inception5h.zip");

            if (File.Exists(modelFile) && File.Exists(labelsFile))
                return;

            Directory.CreateDirectory(dir);
            var wc = new WebClient();
            wc.DownloadFile(url, zipfile);
            ZipFile.ExtractToDirectory(zipfile, dir);
            File.Delete(zipfile);
        }
    }

这里需要注意的是由于需要下载初始Graph和标签,而且是google的站点,所以得使用一些特殊手段。

最终我随便下载了几张图放到bin\Debug\img

 

 然后运行程序,首先确保bin\Debug\tmp文件夹下有tensorflow_inception_graph.pb及imagenet_comp_graph_label_strings.txt。

 

人工智能的魅力非常大,本文只是一个入门,复制上面的代码,你没法训练模型等等操作。所以道路还是很远,需一步一步来。

更多可以查看 https://github.com/migueldeicaza/TensorFlowSharp 及 https://github.com/tensorflow/models

参考文档:

TensorFlow 官网:https://www.tensorflow.org/get_started/

TensorFlow 中文社区:http://www.tensorfly.cn/

TensorFlow 官方文档中文版:http://wiki.jikexueyuan.com/project/tensorflow-zh/

分享到:

发表评论

评论列表