c# 部署onnx分类模型

目录

1.环境

 2.代码

3.效果


1.环境

gpu3060+cuda11.1+vs2019

+Microsoft.ML.OnnxRuntime

+SixLabors.ImageSharp

 2.代码

using System;
using System.Collections.Generic;
using System.Linq;

using Microsoft.ML.OnnxRuntime.Tensors;  // DenseTensor

using SixLabors.ImageSharp;  // Image, Size
using SixLabors.ImageSharp.PixelFormats;  // Rgb24
using SixLabors.ImageSharp.Processing;  // image.Mutate

namespace Microsoft.ML.OnnxRuntime.ResNet50v2Sample
{
    class Program
    {
        public static void Main(string[] args)
        {
            // Read paths
            string modelFilePath = @"E:\code\Csharp\onnxruntime-master\csharp\sample\Microsoft.ML.OnnxRuntime.ResNet50v2Sample\resnet50-v2-7.onnx";
            string imageFilePath = @"E:\code\Csharp\onnxruntime-master\csharp\sample\Microsoft.ML.OnnxRuntime.ResNet50v2Sample\dog.jpeg";

            // Read image
            // Rgb24:Pixel type containing three 8-bit unsigned normalized values ranging from 0 to
            //        255. The color components are stored in red, green, blue order
            // SixLabors.ImageSharp.Image
            using Image image = Image.Load(imageFilePath);  // 以rgb形式读取图片

            // Resize image
            image.Mutate(x =>
            {
                x.Resize(new ResizeOptions
                {
                    Size = new Size(224, 224),
                    Mode = ResizeMode.Crop
                });
            });

            //image.Mutate(x =>
            //        x.Resize(224, 224)
            //);


            // Preprocess image
            Tensor input = new DenseTensor(new[] { 1, 3, 224, 224 });  // 声明4维变量:(b, c, h, w)
            var mean = new[] { 0.485f, 0.456f, 0.406f };
            var stddev = new[] { 0.229f, 0.224f, 0.225f };
            for (int y = 0; y < image.Height; y++)
            {
                Span pixelSpan = image.GetPixelRowSpan(y);
                for (int x = 0; x < image.Width; x++)  // 先行后列
                {
                    input[0, 0, y, x] = ((pixelSpan[x].R / 255f) - mean[0]) / stddev[0];
                    input[0, 1, y, x] = ((pixelSpan[x].G / 255f) - mean[1]) / stddev[1];
                    input[0, 2, y, x] = ((pixelSpan[x].B / 255f) - mean[2]) / stddev[2];
                }
            }

            // Setup inputs
            var inputs = new List
            {
                NamedOnnxValue.CreateFromTensor("data", input)
            };

            // Run inference
            using var session = new InferenceSession(modelFilePath);
            using IDisposableReadOnlyCollection results = session.Run(inputs);

            // Postprocess to get softmax vector
            IEnumerable output = results.First().AsEnumerable();  // First(): The first element in the specified sequence. AsEnumerable:
            float sum = output.Sum(x => (float)Math.Exp(x));   // sum(e^x)
            IEnumerable softmax = output.Select(x => (float)Math.Exp(x) / sum);  // e^x / sum

            // Extract top 10 predicted classes
            IEnumerable top10 = softmax.Select((x, i) => new Prediction { Label = LabelMap.Labels[i], Confidence = x })
                               .OrderByDescending(x => x.Confidence)
                               .Take(10);

            // Print results to console
            Console.WriteLine("Top 10 predictions for ResNet50 v2...");
            Console.WriteLine("--------------------------------------------------------------");
            foreach (var t in top10)
            {
                Console.WriteLine($"Label: {t.Label}, Confidence: {t.Confidence}");
            }
        }
    }
}

3.效果

输入图片:

c# 部署onnx分类模型_第1张图片

网络输出:

 c# 部署onnx分类模型_第2张图片

 第一个是金毛猎犬。

你可能感兴趣的:(C#,onnxruntime,c#,人工智能,深度学习)