機器學習框架ML.NET學習筆記【7】人物圖片顏值判斷

seabluescn發表於2019-05-31

機器學習框架筆記

一、概述

這次要解決的問題是輸入一張照片，輸出人物的顏值資料。

學習樣本來源於華南理工大學釋出的SCUT-FBP5500資料集，資料集包括 5500 人，每人按顏值魅力打分，分值在 1 到 5 分之間。其中包括男性、女性、中國人、外國人四個分類。

SCUT-FBP5500_full.csv檔案標記了每個圖片人物的顏值打分資料。（我把分值一項乘以了20，變成了滿分100分，不影響計算結果）

整個程式處理流程和前一篇圖片分類的基本一致，唯一的區別，分類用的是多元分類演算法，這次採用的是迴歸演算法。

二、原始碼

下面是全部程式碼：

namespace TensorFlow_ImageClassification
{    

    class Program
    {
        //Assets files download from:https://gitee.com/seabluescn/ML_Assets
        static readonly string AssetsFolder = @"D:\StepByStep\Blogs\ML_Assets";
        static readonly string TrainDataFolder = Path.Combine(AssetsFolder, "FaceValueDetection", "SCUT-FBP5500");
        static readonly string TrainTagsPath = Path.Combine(AssetsFolder, "FaceValueDetection", "SCUT-FBP5500_asia_full.csv");
        static readonly string TestDataFolder = Path.Combine(AssetsFolder, "FaceValueDetection", "testimages");
        static readonly string inceptionPb = Path.Combine(AssetsFolder, "TensorFlow", "tensorflow_inception_graph.pb");
        static readonly string imageClassifierZip = Path.Combine(Environment.CurrentDirectory, "MLModel", "imageClassifier.zip");

        //配置用常量
        private struct ImageNetSettings
        {
            public const int imageHeight = 224;
            public const int imageWidth = 224;
            public const float mean = 117;
            public const float scale = 1;
            public const bool channelsLast = true;
        }

        static void Main(string[] args)
        {
            TrainAndSaveModel();
            LoadAndPrediction();

            Console.WriteLine("Hit any key to finish the app");
            Console.ReadKey();
        }

        public static void TrainAndSaveModel()
        {
            MLContext mlContext = new MLContext(seed: 1);

            // STEP 1: 準備資料
            var fulldata = mlContext.Data.LoadFromTextFile<ImageNetData>(path: TrainTagsPath, separatorChar: ',', hasHeader: true);
            var trainTestData = mlContext.Data.TrainTestSplit(fulldata, testFraction: 0.2);
            var trainData = trainTestData.TrainSet;
            var testData = trainTestData.TestSet;

            // STEP 2：建立學習管道
            var pipeline = mlContext.Transforms.LoadImages(outputColumnName: "input", imageFolder: TrainDataFolder, inputColumnName: nameof(ImageNetData.ImagePath))
                .Append(mlContext.Transforms.ResizeImages(outputColumnName: "input", imageWidth: ImageNetSettings.imageWidth, imageHeight: ImageNetSettings.imageHeight, inputColumnName: "input"))
                .Append(mlContext.Transforms.ExtractPixels(outputColumnName: "input", interleavePixelColors: ImageNetSettings.channelsLast, offsetImage: ImageNetSettings.mean))
                .Append(mlContext.Model.LoadTensorFlowModel(inceptionPb).
                     ScoreTensorFlowModel(outputColumnNames: new[] { "softmax2_pre_activation" }, inputColumnNames: new[] { "input" }, addBatchDimensionInput: true))
                .Append(mlContext.Regression.Trainers.LbfgsPoissonRegression(labelColumnName: "Label", featureColumnName: "softmax2_pre_activation"));


            // STEP 3：通過訓練資料調整模型             
            ITransformer model = pipeline.Fit(trainData);          

            // STEP 4：評估模型           
            var predictions = model.Transform(testData); 
            var metrics = mlContext.Regression.Evaluate(predictions, labelColumnName: "Label", scoreColumnName: "Score");
            PrintRegressionMetrics( metrics);          

            //STEP 5：儲存模型
            Console.WriteLine("====== Save model to local file =========");
            mlContext.Model.Save(model, trainData.Schema, imageClassifierZip);
        }

        static void LoadAndPrediction()
        {
            MLContext mlContext = new MLContext(seed: 1);

            // Load the model
            ITransformer loadedModel = mlContext.Model.Load(imageClassifierZip, out var modelInputSchema);

            // Make prediction function (input = ImageNetData, output = ImageNetPrediction)
            var predictor = mlContext.Model.CreatePredictionEngine<ImageNetData, ImageNetPrediction>(loadedModel);
            
            DirectoryInfo testdir = new DirectoryInfo(TestDataFolder);
            foreach (var jpgfile in testdir.GetFiles("*.jpg"))
            {
                ImageNetData image = new ImageNetData();
                image.ImagePath = jpgfile.FullName;
                var pred = predictor.Predict(image);

                Console.WriteLine($"Filename:{jpgfile.Name}:\tPredict Result:{pred.FaceValue}");
            }
        }       
    }

    public class ImageNetData
    {
        [LoadColumn(0)]
        public string ImagePath;

        [LoadColumn(1)]
        public float Label;
    }

    public class ImageNetPrediction
    {
        [ColumnName("Score")]
        public float FaceValue;
    }   
}

View Code

三、分析

1、資料處理通道

// STEP 2：建立學習管道
var pipeline = mlContext.Transforms.LoadImages(...)
    .Append(mlContext.Transforms.ResizeImages(...)
    .Append(mlContext.Transforms.ExtractPixels(...)
    .Append(mlContext.Model.LoadTensorFlowModel(inceptionPb)
        .ScoreTensorFlowModel(outputColumnNames: new[] { "softmax2_pre_activation" }, inputColumnNames: new[] { "input" }, addBatchDimensionInput: true))    
    .Append(mlContext.Regression.Trainers.LbfgsPoissonRegression(labelColumnName: "Label", featureColumnName: "softmax2_pre_activation"));