C# Onnx PP-HumanSeg 人像分割

效果

模型信息

项目

代码

下载

效果

图片源自网络侵删

模型信息

Inputs
-------------------------
name：x
tensor：Float[1, 3, 192, 192]
---------------------------------------------------------------

Outputs
-------------------------
name：tf.identity
tensor：Float[1, 192, 192, 2]
---------------------------------------------------------------

项目

VS2022

.net framework 4.8

OpenCvSharp 4.8

Microsoft.ML.OnnxRuntime 1.16.2

代码

using Microsoft.ML.OnnxRuntime.Tensors;
using Microsoft.ML.OnnxRuntime;
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Windows.Forms;
using System.Linq;
using System.Drawing;

namespace Onnx_Demo
{
public partial class frmMain : Form
{
public frmMain()
{
InitializeComponent();
}

string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
string image_path = "";

DateTime dt1 = DateTime.Now;
DateTime dt2 = DateTime.Now;

float conf_threshold = 0.9f;

int inpWidth;
int inpHeight;

int outHeight, outWidth;

Mat image;

string model_path = "";

SessionOptions options;
InferenceSession onnx_session;
Tensor<float> input_tensor;
List<NamedOnnxValue> input_ontainer;

IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
DisposableNamedOnnxValue[] results_onnxvalue;

private void button1_Click(object sender, EventArgs e)
{
OpenFileDialog ofd = new OpenFileDialog();
ofd.Filter = fileFilter;
if (ofd.ShowDialog() != DialogResult.OK) return;

pictureBox1.Image = null;
pictureBox2.Image = null;
textBox1.Text = "";

image_path = ofd.FileName;
pictureBox1.Image = new System.Drawing.Bitmap(image_path);
image = new Mat(image_path);
}

private void Form1_Load(object sender, EventArgs e)
{
// 创建输入容器
input_ontainer = new List<NamedOnnxValue>();

// 创建输出会话
options = new SessionOptions();
options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行

// 创建推理模型类，读取本地模型文件
model_path = "model/model_float32.onnx";

inpHeight = 192;
inpWidth = 192;

outHeight = 192;
outWidth = 192;

onnx_session = new InferenceSession(model_path, options);

// 创建输入容器
input_ontainer = new List<NamedOnnxValue>();

image_path = "test_img/1.jpg";
pictureBox1.Image = new Bitmap(image_path);

}

private unsafe void button2_Click(object sender, EventArgs e)
{
if (image_path == "")
{
return;
}
textBox1.Text = "检测中，请稍等……";
pictureBox2.Image = null;
System.Windows.Forms.Application.DoEvents();

image = new Mat(image_path);

Mat resize_image = new Mat();
Cv2.Resize(image, resize_image, new OpenCvSharp.Size(inpWidth, inpHeight));

float[] input_tensor_data = new float[1 * 3 * inpWidth * inpHeight];
int row = resize_image.Rows;
int col = resize_image.Cols;
for (int c = 0; c < 3; c++)
{
for (int i = 0; i < inpHeight; i++)
{
for (int j = 0; j < inpWidth; j++)
{
byte pix = ((byte*)(resize_image.Ptr(i).ToPointer()))[j * 3 + c];
input_tensor_data[c * row * col + i * col + j] = (float)((pix / 255.0-0.5)/0.5);
}
}
}

input_tensor = new DenseTensor<float>(input_tensor_data, new[] { 1, 3, inpHeight, inpWidth });

//将 input_tensor 放入一个输入参数的容器，并指定名称
input_ontainer.Add(NamedOnnxValue.CreateFromTensor("x", input_tensor));

dt1 = DateTime.Now;
//运行 Inference 并获取结果
result_infer = onnx_session.Run(input_ontainer);
dt2 = DateTime.Now;

//将输出结果转为DisposableNamedOnnxValue数组
results_onnxvalue = result_infer.ToArray();

float[] mask = results_onnxvalue[0].AsTensor<float>().ToArray();

Mat mask_out = new Mat(outHeight, outWidth, MatType.CV_32FC2, mask);

Cv2.Resize(mask_out, mask_out, new OpenCvSharp.Size(image.Cols, image.Rows));

Mat result_image = image.Clone();

for (int h = 0; h < result_image.Rows; h++)
{
for (int w = 0; w < result_image.Cols; w++)
{
float pix = mask_out.At<float>(h, w);
if (pix > conf_threshold)
{
Vec3b vec3B = result_image.At<Vec3b>(h, w);

vec3B.Item0 = 0;
vec3B.Item1 = 255;
vec3B.Item2 = 0;

result_image.Set<Vec3b>(h, w, vec3B);
}
}
}

if (pictureBox2.Image != null)
{
pictureBox2.Image.Dispose();
}

pictureBox2.Image = new System.Drawing.Bitmap(result_image.ToMemoryStream());
textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

mask_out.Dispose();
image.Dispose();
resize_image.Dispose();
result_image.Dispose();
}

private void pictureBox2_DoubleClick(object sender, EventArgs e)
{
Common.ShowNormalImg(pictureBox2.Image);
}

private void pictureBox1_DoubleClick(object sender, EventArgs e)
{
Common.ShowNormalImg(pictureBox1.Image);
}
}
}

using Microsoft.ML.OnnxRuntime.Tensors;
using Microsoft.ML.OnnxRuntime;
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Windows.Forms;
using System.Linq;
using System.Drawing;

namespace Onnx_Demo
{
    public partial class frmMain : Form
    {
        public frmMain()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;

        float conf_threshold = 0.9f;

        int inpWidth;
        int inpHeight;

        int outHeight, outWidth;

        Mat image;

        string model_path = "";

        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        List<NamedOnnxValue> input_ontainer;

        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;

            pictureBox1.Image = null;
            pictureBox2.Image = null;
            textBox1.Text = "";

            image_path = ofd.FileName;
            pictureBox1.Image = new System.Drawing.Bitmap(image_path);
            image = new Mat(image_path);
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            // 创建输入容器
            input_ontainer = new List<NamedOnnxValue>();

            // 创建输出会话
            options = new SessionOptions();
            options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
            options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行

            // 创建推理模型类，读取本地模型文件
            model_path = "model/model_float32.onnx";

            inpHeight = 192;
            inpWidth = 192;

            outHeight = 192;
            outWidth = 192;

            onnx_session = new InferenceSession(model_path, options);

            // 创建输入容器
            input_ontainer = new List<NamedOnnxValue>();

            image_path = "test_img/1.jpg";
            pictureBox1.Image = new Bitmap(image_path);

        }

        private unsafe void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }
            textBox1.Text = "检测中，请稍等……";
            pictureBox2.Image = null;
            System.Windows.Forms.Application.DoEvents();

            image = new Mat(image_path);

            Mat resize_image = new Mat();
            Cv2.Resize(image, resize_image, new OpenCvSharp.Size(inpWidth, inpHeight));

            float[] input_tensor_data = new float[1 * 3 * inpWidth * inpHeight];
            int row = resize_image.Rows;
            int col = resize_image.Cols;
            for (int c = 0; c < 3; c++)
            {
                for (int i = 0; i < inpHeight; i++)
                {
                    for (int j = 0; j < inpWidth; j++)
                    {
                        byte pix = ((byte*)(resize_image.Ptr(i).ToPointer()))[j * 3 + c];
                        input_tensor_data[c * row * col + i * col + j] = (float)((pix / 255.0-0.5)/0.5);
                    }
                }
            }

            input_tensor = new DenseTensor<float>(input_tensor_data, new[] { 1, 3, inpHeight, inpWidth });

            //将 input_tensor 放入一个输入参数的容器，并指定名称
            input_ontainer.Add(NamedOnnxValue.CreateFromTensor("x", input_tensor));

            dt1 = DateTime.Now;
            //运行 Inference 并获取结果
            result_infer = onnx_session.Run(input_ontainer);
            dt2 = DateTime.Now;

            //将输出结果转为DisposableNamedOnnxValue数组
            results_onnxvalue = result_infer.ToArray();

            float[] mask = results_onnxvalue[0].AsTensor<float>().ToArray();

            Mat mask_out = new Mat(outHeight, outWidth, MatType.CV_32FC2, mask);

            Cv2.Resize(mask_out, mask_out, new OpenCvSharp.Size(image.Cols, image.Rows));

            Mat result_image = image.Clone();

            for (int h = 0; h < result_image.Rows; h++)
            {
                for (int w = 0; w < result_image.Cols; w++)
                {
                    float pix = mask_out.At<float>(h, w);
                    if (pix > conf_threshold)
                    {
                        Vec3b vec3B = result_image.At<Vec3b>(h, w);

                        vec3B.Item0 = 0;
                        vec3B.Item1 = 255;
                        vec3B.Item2 = 0;

                        result_image.Set<Vec3b>(h, w, vec3B);
                    }
                }
            }

            if (pictureBox2.Image != null)
            {
                pictureBox2.Image.Dispose();
            }

            pictureBox2.Image = new System.Drawing.Bitmap(result_image.ToMemoryStream());
            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

            mask_out.Dispose();
            image.Dispose();
            resize_image.Dispose();
            result_image.Dispose();
        }

        private void pictureBox2_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox2.Image);
        }

        private void pictureBox1_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox1.Image);
        }
    }
}