我已经使用Azure Custom Vision训练了一个模型（对象检测），并将模型导出为ONNX，然后将模型导入到我的WPF（.net core）项目中。
我使用ML.net从我的模型中得到预测，我发现结果与我在Custom Vision上看到的预测有巨大的不同。
我已经尝试了不同的提取顺序（ABGR，ARGB等），但结果是非常失望的，任何人可以给予我一些建议，因为没有这么多的在线文档关于使用自定义视觉的ONNX模型与WPF做对象检测。
下面是一些片段：

// Model creation and pipeline definition for images needs to run just once, so calling it from the constructor:
        var pipeline = mlContext.Transforms
            .ResizeImages(
                resizing: ImageResizingEstimator.ResizingKind.Fill,
                outputColumnName: MLObjectDetectionSettings.InputTensorName,
                imageWidth: MLObjectDetectionSettings.ImageWidth,
                imageHeight: MLObjectDetectionSettings.ImageHeight,
                inputColumnName: nameof(MLObjectDetectionInputData.Image))
            .Append(mlContext.Transforms.ExtractPixels(
                colorsToExtract: ImagePixelExtractingEstimator.ColorBits.Rgb,
                orderOfExtraction: ImagePixelExtractingEstimator.ColorsOrder.ABGR,
                outputColumnName: MLObjectDetectionSettings.InputTensorName))
            .Append(mlContext.Transforms.ApplyOnnxModel(modelFile: modelPath, outputColumnName: MLObjectDetectionSettings.OutputTensorName, inputColumnName: MLObjectDetectionSettings.InputTensorName));

        //Create empty DataView. We just need the schema to call fit()
        var emptyData = new List<MLObjectDetectionInputData>();
        var dataView = mlContext.Data.LoadFromEnumerable(emptyData);

        //Generate a model.
        var model = pipeline.Fit(dataView);

然后我用这个模型来创建上下文。

//Create prediction engine.
            var predictionEngine = _mlObjectDetectionContext.Model.CreatePredictionEngine<MLObjectDetectionInputData, MLObjectDetectionPrediction>(_mlObjectDetectionModel);

            //Load tag labels.
            var labels = File.ReadAllLines(LABELS_OBJECT_DETECTION_FILE_PATH);

            //Create input data.
            var imageInput = new MLObjectDetectionInputData { Image = this.originalImage };

            //Predict.
            var prediction = predictionEngine.Predict(imageInput);