我在尝试让我的第一个图像分类模型工作，然而，VNClassificationObservation不起作用，而VNCoreMLFeatureValueObservation可以工作。
这是我的模型的一些信息：
MLModelDescription: MLModelDescription inputDescriptionsByName: {"input_1__0" = "input_1__0 : Image (Color, 299 x 299)";} outputDescriptionsByName: { "output_node0__0" = "output_node0__0 : MultiArray (MLMultiArrayDataTypeDouble, 43)";} predictedFeatureName: (null) 根据文档：
VNClassificationObservation这种类型的观察结果来自于使用角色为分类（而不是预测或图像到图像处理）的Core ML模型执行VNCoreMLRequest图像分析。Vision推断一个MLModel对象是分类器模型，如果该模型预测单一特征。即，该模型的modelDescription对象的predictedFeatureName属性有一个非nil值。起初我以为文档中所说的“预测”是指回归类型模型的值预测。但现在我想他们指的是softmax预测概率？因此，VNClassificationObservation不输出softmax预测概率。
现在，
VNCoreMLFeatureValueObservation:概述这种类型的观察结果来自于使用角色为预测而不是分类或图像到图像处理的Core ML模型执行VNCoreMLRequest图像分析。Vision推断一个MLModel对象是预测器模型，如果该模型预测多个特征。你可以通过查看模型的modelDescription对象的predictedFeatureName属性是否为nil，或者它是否将其输出插入到outputDescriptionsByName字典中，来判断一个模型是否预测多个特征。我对这些措辞感到困惑。这是否意味着多输入、多输出的模型？不是分类，而是预测，这也有点令人困惑，但我假设是softmax概率，因为我得到的输出是这样。
当我运行下面的代码时，我得到：
let request = VNCoreMLRequest(model: model) { [weak self] request, error in guard let results = request.results as? [VNCoreMLFeatureValueObservation], let topResult = results.first else { fatalError("unexpected result type from VNCoreMLRequest")DispatchQueue.main.async { [weak self] in print("topResult!", topResult) //print(model.debugDescription.outputDescriptionsByName) } } let handler = VNImageRequestHandler(ciImage: image) DispatchQueue.global(qos: .userInteractive).async { do { try handler.perform([request]) } catch {print(error)}我得到一堆值：
topResult! Optional(<VNCoreMLFeatureValueObservation: 0x1c003f0c0> C99BC0A0-7722-4DDC-8FB8-C0FEB1CEEFA5 1 "MultiArray : Double 43 vector[ 0.02323521859943867,0.03784361109137535,0.0327669121325016,0.02373981475830078,0.01920632272958755,0.01511944644153118,0.0268220379948616,0.00990589614957571,0.006585873663425446,0.02727104164659977,0.02337176166474819,0.0177282840013504,0.01582957617938519,0.01962342299520969,0.0335112139582634,0.01197215262800455,0.04638960584998131,0.0546870082616806,0.008390620350837708,0.02519697323441505,0.01038128975778818,0.02463733218610287,0.05725555866956711,0.02852404117584229,0.01987413503229618,0.02478211745619774,0.01224409975111485,0.03397252038121223,0.02300941571593285,0.02020683139562607,0.03740271925926208,0.01999092660844326,0.03210178017616272,0.02830206602811813,0.01122485008090734,0.01071082800626755,0.02285266295075417,0.01730070635676384,0.009790488518774509,0.01149104069918394,0.03331543132662773,0.01211327593773603,0.0193191897124052]" (1.000000))如果这些确实是softmax概率，我该如何获取最大值的索引？我似乎无法使用.count或类似的数组方法。
我尝试将其转换为数组，但这两种方法都不起作用
let values = topResult.featureValue as Array! (无法转换...强制转换)let values = topResult as Array!如果这些不是softmax值/概率，那么我该如何获取概率值。我正在尝试获取前3个softmax概率的索引。
谢谢你。
!!!更新!!!!!!!!:
尝试在函数中这样做：var localPrediction: String? let topResult = results.first?.featureValue.multiArrayValue
DispatchQueue.main.async { () in var max_value : Float32 = 0 for i in 0..<topResult!.count{ if max_value < topResult![i].floatValue{ max_value = topResult![i].floatValue localPrediction = String(i)} }回答：
当你的模型是分类器，即mlmodel文件中的NeuralNetworkClassifier时，输出是VNClassificationObservation对象。
当你的模型不是分类器，即NeuralNetwork或NeuralNetworkRegressor时，输出是一个或多个包含你最终层输出的VNCoreMLFeatureValueObservation对象。
所以，如果你期望在VNCoreMLFeatureValueObservation中得到softmax输出，你需要确保你的模型的最终层是softmax。
要获取最大元素的索引和值，请使用：
func argmax(_ array: UnsafePointer<Double>, count: Int) -> (Int, Double) { var maxValue: Double = 0 var maxIndex: vDSP_Length = 0 vDSP_maxviD(array, 1, &maxValue, &maxIndex, vDSP_Length(count)) return (Int(maxIndex), maxValue)}要使用它，首先将MLMultiArray的dataPointer转换为UnsafePointer<Double>，然后调用argmax()函数：
let featurePointer = UnsafePointer<Double>(OpaquePointer(features.dataPointer))let (maxIndex, maxValue) = argmax(featurePointer, 43)