cntk - 如何使用 RGB 图像作为 C# EvalDll Wrapper 的输入？

Question

我使用提供的 ImageReader 训练了一个网络，现在，我尝试在 C# 项目中使用 CNTK EvalDll 来评估 RGB 图像。

我见过与 EvalDll 相关的示例，但输入始终是浮点/ double 组，而不是图像。

如何使用公开的接口(interface)将经过训练的网络与 RGB 图像一起使用？

Answer 1

我假设您希望使用 ImageReader 进行阅读，您的阅读器配置类似于

features=[
        width=224
        height=224
        channels=3
        cropType=Center
]

您需要辅助函数来创建裁剪并将图像调整为网络接受的大小。

我将定义 2 个 System.Drawing.Bitmap 的扩展方法，一个用于裁剪，一个用于调整大小:

open System.Collections.Generic
open System.Drawing
open System.Drawing.Drawing2D
open System.Drawing.Imaging
type Bitmap with
    /// Crops the image in the present object, starting at the given (column, row), and retaining
    /// the given number of columns and rows.
    member this.Crop(column, row, numCols, numRows) = 
        let rect = Rectangle(column, row, numCols, numRows)
        this.Clone(rect, this.PixelFormat)
    /// Creates a resized version of the present image. The returned image
    /// will have the given width and height. This may distort the aspect ratio
    /// of the image.
    member this.ResizeImage(width, height, useHighQuality) =
        // Rather than using image.GetThumbnailImage, use direct image resizing.
        // GetThumbnailImage throws odd out-of-memory exceptions on some 
        // images, see also 
        // http://stackoverflow.com/questions/27528057/c-sharp-out-of-memory-exception-in-getthumbnailimage-on-a-server
        // Use the interpolation method suggested on 
        // http://stackoverflow.com/questions/1922040/resize-an-image-c-sharp
        let rect = Rectangle(0, 0, width, height);
        let destImage = new Bitmap(width, height);
        destImage.SetResolution(this.HorizontalResolution, this.VerticalResolution);
        use graphics = Graphics.FromImage destImage
        graphics.CompositingMode <- CompositingMode.SourceCopy;
        if useHighQuality then
            graphics.InterpolationMode <- InterpolationMode.HighQualityBicubic
            graphics.CompositingQuality <- CompositingQuality.HighQuality
            graphics.SmoothingMode <- SmoothingMode.HighQuality
            graphics.PixelOffsetMode <- PixelOffsetMode.HighQuality
        else
            graphics.InterpolationMode <- InterpolationMode.Low
        use wrapMode = new ImageAttributes()
        wrapMode.SetWrapMode WrapMode.TileFlipXY
        graphics.DrawImage(this, rect, 0, 0, this.Width,this.Height, GraphicsUnit.Pixel, wrapMode)
        destImage

在此基础上，定义一个函数来做中心裁剪:

/// Returns a square sub-image from the center of the given image, with
/// a size that is cropRatio times the smallest image dimension. The 
/// aspect ratio is preserved.
let CenterCrop cropRatio (image: Bitmap) =
    let cropSize = 
        float(min image.Height image.Width) * cropRatio
        |> int
    let startRow = (image.Height - cropSize) / 2
    let startCol = (image.Width - cropSize) / 2
    image.Crop(startCol, startRow, cropSize, cropSize)

然后将它们全部插入:裁剪、调整大小，然后按照 OpenCV 使用的平面顺序遍历图像:

/// Creates a list of CNTK feature values from a given bitmap.
/// The image is first resized to fit into an (targetSize x targetSize) bounding box,
/// then the image planes are converted to a CNTK tensor.
/// Returns a list with targetSize*targetSize*3 values.
let ImageToFeatures (image: Bitmap, targetSize) =
    // Apply the same image pre-processing that is typically done
    // in CNTK when running it in test or write mode: Take a center
    // crop of the image, then re-size it to the network input size.
    let cropped = CenterCrop 1.0 image
    let resized = cropped.ResizeImage(targetSize, targetSize, false)
    // Ensure that the initial capacity of the list is provided 
    // with the constructor. Creating the list via the default constructor
    // makes the whole operation 20% slower.
    let features = List (targetSize * targetSize * 3)
    // Traverse the image in the format that is used in OpenCV:
    // First the B plane, then the G plane, R plane
    for c in 0 .. 2 do
        for h in 0 .. (resized.Height - 1) do
            for w in 0 .. (resized.Width - 1) do
                let pixel = resized.GetPixel(w, h)
                let v = 
                    match c with 
                    | 0 -> pixel.B
                    | 1 -> pixel.G
                    | 2 -> pixel.R
                    | _ -> failwith "No such channel"
                    |> float32
                features.Add v
    features

使用相关图像调用 ImageToFeatures，将结果提供给 IEvaluateModelManagedF 实例，就可以了。我假设您的 RGB 图像来自 myImage，并且您正在使用 224 x 224 的网络大小进行二进制分类。

let LoadModelOnCpu modelPath =
    let model = new IEvaluateModelManagedF()
    let description = sprintf "deviceId=-1\r\nmodelPath=\"%s\"" modelPath
    model.Init description
    model.CreateNetwork description
    model
let model = LoadModelOnCpu("myModelFile")
let featureDict = Dictionary()
featureDict.["features"] <- ImageToFeatures(myImage, 224)
model.Evaluate(featureDict, "OutputNodes.z", 2)