目录

介绍

效果

模型信息

项目

代码

下载

---

C# Onnx 使用onnxruntime部署实时视频帧插值

介绍

github地址：https://github.com/google-research/frame-interpolation

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

The official Tensorflow 2 implementation of our high quality frame interpolation neural network. We present a unified single-network approach that doesn't use additional pre-trained networks, like optical flow or depth, and yet achieve state-of-the-art results. We use a multi-scale feature extractor that shares the same convolution weights across the scales. Our model is trainable from frame triplets alone.

FILM transforms near-duplicate photos into a slow motion footage that look like it is shot with a video camera.

效果

模型信息

Model Properties
-------------------------
---------------------------------------------------------------

Inputs
-------------------------
name：I0
tensor：Float[1, 3, -1, -1]
name：I1
tensor：Float[1, 3, -1, -1]
---------------------------------------------------------------

Outputs
-------------------------
name：merged
tensor：Float[1, -1, -1, -1]
---------------------------------------------------------------

项目

代码

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

namespace Onnx_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string startupPath;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;
        Mat result_image;

        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        Tensor<float> input_tensor2;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;

        Tensor<float> result_tensors;
        float[] result_array;

        float[] input1_image;
        float[] input2_image;

        int inpWidth;
        int inpHeight;

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        void Preprocess(Mat img, ref float[] input_img)
        {
            Mat rgbimg = new Mat();
            Cv2.CvtColor(img, rgbimg, ColorConversionCodes.BGR2RGB);
            int h = rgbimg.Rows;
            int w = rgbimg.Cols;
            int align = 32;
            if (h % align != 0 || w % align != 0)
            {
                int ph = ((h - 1) / align + 1) * align;
                int pw = ((w - 1) / align + 1) * align;

                Cv2.CopyMakeBorder(rgbimg, rgbimg, 0, ph - h, 0, pw - w, BorderTypes.Constant, 0);
            }

            inpHeight = rgbimg.Rows;
            inpWidth = rgbimg.Cols;

            rgbimg.ConvertTo(rgbimg, MatType.CV_32FC3, 1 / 255.0);

            int image_area = rgbimg.Rows * rgbimg.Cols;

            //input_img = new float[3 * image_area];

            input_img = Common.ExtractMat(rgbimg);

        }

        Mat Interpolate(Mat srcimg1, Mat srcimg2)
        {
            int srch = srcimg1.Rows;
            int srcw = srcimg1.Cols;

            Preprocess(srcimg1, ref input1_image);
            Preprocess(srcimg2, ref input2_image);

            // 输入Tensor
            input_tensor = new DenseTensor<float>(input1_image, new[] { 1, 3, inpHeight, inpWidth });
            input_tensor2 = new DenseTensor<float>(input2_image, new[] { 1, 3, inpHeight, inpWidth });

            //将tensor 放入一个输入参数的容器，并指定名称
            input_container.Add(NamedOnnxValue.CreateFromTensor("I0", input_tensor));
            input_container.Add(NamedOnnxValue.CreateFromTensor("I1", input_tensor2));

            //运行 Inference 并获取结果
            result_infer = onnx_session.Run(input_container);

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

            // 读取第一个节点输出并转为Tensor数据
            result_tensors = results_onnxvalue[0].AsTensor<float>();

            int out_h = results_onnxvalue[0].AsTensor<float>().Dimensions[2];
            int out_w = results_onnxvalue[0].AsTensor<float>().Dimensions[3];

            result_array = result_tensors.ToArray();

            for (int i = 0; i < result_array.Length; i++)
            {
                result_array[i] = result_array[i] * 255;

                if (result_array[i] < 0)
                {
                    result_array[i] = 0;
                }
                else if (result_array[i] > 255)
                {
                    result_array[i] = 255;
                }

                result_array[i] = result_array[i] + 0.5f;
            }

            float[] temp_r = new float[out_h * out_w];
            float[] temp_g = new float[out_h * out_w];
            float[] temp_b = new float[out_h * out_w];

            Array.Copy(result_array, temp_r, out_h * out_w);
            Array.Copy(result_array, out_h * out_w, temp_g, 0, out_h * out_w);
            Array.Copy(result_array, out_h * out_w * 2, temp_b, 0, out_h * out_w);

            Mat rmat = new Mat(out_h, out_w, MatType.CV_32F, temp_r);
            Mat gmat = new Mat(out_h, out_w, MatType.CV_32F, temp_g);
            Mat bmat = new Mat(out_h, out_w, MatType.CV_32F, temp_b);

            result_image = new Mat();
            Cv2.Merge(new Mat[] { bmat, gmat, rmat }, result_image);

            result_image.ConvertTo(result_image, MatType.CV_8UC3);

            Mat mid_img = new Mat(result_image, new Rect(0, 0, srcw, srch));

            return mid_img;

        }

        private void button2_Click(object sender, EventArgs e)
        {
            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "正在运行，请稍后……";
            Application.DoEvents();

            dt1 = DateTime.Now;

            List<String> inputs_imgpath = new List<String>() { "test_img/frame07.png", "test_img/frame08.png", "test_img/frame09.png", "test_img/frame10.png", "test_img/frame11.png", "test_img/frame12.png", "test_img/frame13.png", "test_img/frame14.png" };

            int imgnum = inputs_imgpath.Count();

            for (int i = 0; i < imgnum - 1; i++)
            {
                Mat srcimg1 = Cv2.ImRead(inputs_imgpath[i]);
                Mat srcimg2 = Cv2.ImRead(inputs_imgpath[i + 1]);

                Mat mid_img = Interpolate(srcimg1, srcimg2);

                string save_imgpath = "imgs_results/mid" + i + ".jpg";
                Cv2.ImWrite(save_imgpath, mid_img);
            }

            dt2 = DateTime.Now;

            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
            button2.Enabled = true;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            model_path = "model/RIFE_HDv3.onnx";

            // 创建输出会话，用于输出模型读取信息
            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
            onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径

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

            pictureBox1.Image = new Bitmap("test_img/frame11.png");
            pictureBox3.Image = new Bitmap("test_img/frame12.png");

        }

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

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

        SaveFileDialog sdf = new SaveFileDialog();
        private void button3_Click(object sender, EventArgs e)
        {
            if (pictureBox2.Image == null)
            {
                return;
            }
            Bitmap output = new Bitmap(pictureBox2.Image);
            sdf.Title = "保存";
            sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp|Images (*.emf)|*.emf|Images (*.exif)|*.exif|Images (*.gif)|*.gif|Images (*.ico)|*.ico|Images (*.tiff)|*.tiff|Images (*.wmf)|*.wmf";
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                switch (sdf.FilterIndex)
                {
                    case 1:
                        {
                            output.Save(sdf.FileName, ImageFormat.Jpeg);
                            break;
                        }
                    case 2:
                        {
                            output.Save(sdf.FileName, ImageFormat.Png);
                            break;
                        }
                    case 3:
                        {
                            output.Save(sdf.FileName, ImageFormat.Bmp);
                            break;
                        }
                    case 4:
                        {
                            output.Save(sdf.FileName, ImageFormat.Emf);
                            break;
                        }
                    case 5:
                        {
                            output.Save(sdf.FileName, ImageFormat.Exif);
                            break;
                        }
                    case 6:
                        {
                            output.Save(sdf.FileName, ImageFormat.Gif);
                            break;
                        }
                    case 7:
                        {
                            output.Save(sdf.FileName, ImageFormat.Icon);
                            break;
                        }

                    case 8:
                        {
                            output.Save(sdf.FileName, ImageFormat.Tiff);
                            break;
                        }
                    case 9:
                        {
                            output.Save(sdf.FileName, ImageFormat.Wmf);
                            break;
                        }
                }
                MessageBox.Show("保存成功，位置：" + sdf.FileName);
            }
        }

        private void button4_Click(object sender, EventArgs e)
        {
            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "正在运行，请稍后……";
            Application.DoEvents();

            dt1 = DateTime.Now;

            Mat srcimg1 = Cv2.ImRead("test_img/frame11.png");
            Mat srcimg2 = Cv2.ImRead("test_img/frame12.png");

            Mat mid_img = Interpolate(srcimg1, srcimg2);

            dt2 = DateTime.Now;

            pictureBox2.Image = new Bitmap(mid_img.ToMemoryStream());

            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
            button2.Enabled = true;
        }
    }
}

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

namespace Onnx_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string startupPath;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;
        Mat result_image;

        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        Tensor<float> input_tensor2;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;

        Tensor<float> result_tensors;
        float[] result_array;

        float[] input1_image;
        float[] input2_image;

        int inpWidth;
        int inpHeight;

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        void Preprocess(Mat img, ref float[] input_img)
        {
            Mat rgbimg = new Mat();
            Cv2.CvtColor(img, rgbimg, ColorConversionCodes.BGR2RGB);
            int h = rgbimg.Rows;
            int w = rgbimg.Cols;
            int align = 32;
            if (h % align != 0 || w % align != 0)
            {
                int ph = ((h - 1) / align + 1) * align;
                int pw = ((w - 1) / align + 1) * align;

                Cv2.CopyMakeBorder(rgbimg, rgbimg, 0, ph - h, 0, pw - w, BorderTypes.Constant, 0);
            }

            inpHeight = rgbimg.Rows;
            inpWidth = rgbimg.Cols;

            rgbimg.ConvertTo(rgbimg, MatType.CV_32FC3, 1 / 255.0);

            int image_area = rgbimg.Rows * rgbimg.Cols;

            //input_img = new float[3 * image_area];

            input_img = Common.ExtractMat(rgbimg);

        }

        Mat Interpolate(Mat srcimg1, Mat srcimg2)
        {
            int srch = srcimg1.Rows;
            int srcw = srcimg1.Cols;

            Preprocess(srcimg1, ref input1_image);
            Preprocess(srcimg2, ref input2_image);

            // 输入Tensor
            input_tensor = new DenseTensor<float>(input1_image, new[] { 1, 3, inpHeight, inpWidth });
            input_tensor2 = new DenseTensor<float>(input2_image, new[] { 1, 3, inpHeight, inpWidth });

            //将tensor 放入一个输入参数的容器，并指定名称
            input_container.Add(NamedOnnxValue.CreateFromTensor("I0", input_tensor));
            input_container.Add(NamedOnnxValue.CreateFromTensor("I1", input_tensor2));

            //运行 Inference 并获取结果
            result_infer = onnx_session.Run(input_container);

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

            // 读取第一个节点输出并转为Tensor数据
            result_tensors = results_onnxvalue[0].AsTensor<float>();

            int out_h = results_onnxvalue[0].AsTensor<float>().Dimensions[2];
            int out_w = results_onnxvalue[0].AsTensor<float>().Dimensions[3];

            result_array = result_tensors.ToArray();

            for (int i = 0; i < result_array.Length; i++)
            {
                result_array[i] = result_array[i] * 255;

                if (result_array[i] < 0)
                {
                    result_array[i] = 0;
                }
                else if (result_array[i] > 255)
                {
                    result_array[i] = 255;
                }

                result_array[i] = result_array[i] + 0.5f;
            }

            float[] temp_r = new float[out_h * out_w];
            float[] temp_g = new float[out_h * out_w];
            float[] temp_b = new float[out_h * out_w];

            Array.Copy(result_array, temp_r, out_h * out_w);
            Array.Copy(result_array, out_h * out_w, temp_g, 0, out_h * out_w);
            Array.Copy(result_array, out_h * out_w * 2, temp_b, 0, out_h * out_w);

            Mat rmat = new Mat(out_h, out_w, MatType.CV_32F, temp_r);
            Mat gmat = new Mat(out_h, out_w, MatType.CV_32F, temp_g);
            Mat bmat = new Mat(out_h, out_w, MatType.CV_32F, temp_b);

            result_image = new Mat();
            Cv2.Merge(new Mat[] { bmat, gmat, rmat }, result_image);

            result_image.ConvertTo(result_image, MatType.CV_8UC3);

            Mat mid_img = new Mat(result_image, new Rect(0, 0, srcw, srch));

            return mid_img;

        }

        private void button2_Click(object sender, EventArgs e)
        {
            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "正在运行，请稍后……";
            Application.DoEvents();

            dt1 = DateTime.Now;

            List<String> inputs_imgpath = new List<String>() { "test_img/frame07.png", "test_img/frame08.png", "test_img/frame09.png", "test_img/frame10.png", "test_img/frame11.png", "test_img/frame12.png", "test_img/frame13.png", "test_img/frame14.png" };

            int imgnum = inputs_imgpath.Count();

            for (int i = 0; i < imgnum - 1; i++)
            {
                Mat srcimg1 = Cv2.ImRead(inputs_imgpath[i]);
                Mat srcimg2 = Cv2.ImRead(inputs_imgpath[i + 1]);

                Mat mid_img = Interpolate(srcimg1, srcimg2);

                string save_imgpath = "imgs_results/mid" + i + ".jpg";
                Cv2.ImWrite(save_imgpath, mid_img);
            }

            dt2 = DateTime.Now;

            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
            button2.Enabled = true;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            model_path = "model/RIFE_HDv3.onnx";

            // 创建输出会话，用于输出模型读取信息
            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
            onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径

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

            pictureBox1.Image = new Bitmap("test_img/frame11.png");
            pictureBox3.Image = new Bitmap("test_img/frame12.png");

        }

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

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

        SaveFileDialog sdf = new SaveFileDialog();
        private void button3_Click(object sender, EventArgs e)
        {
            if (pictureBox2.Image == null)
            {
                return;
            }
            Bitmap output = new Bitmap(pictureBox2.Image);
            sdf.Title = "保存";
            sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp|Images (*.emf)|*.emf|Images (*.exif)|*.exif|Images (*.gif)|*.gif|Images (*.ico)|*.ico|Images (*.tiff)|*.tiff|Images (*.wmf)|*.wmf";
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                switch (sdf.FilterIndex)
                {
                    case 1:
                        {
                            output.Save(sdf.FileName, ImageFormat.Jpeg);
                            break;
                        }
                    case 2:
                        {
                            output.Save(sdf.FileName, ImageFormat.Png);
                            break;
                        }
                    case 3:
                        {
                            output.Save(sdf.FileName, ImageFormat.Bmp);
                            break;
                        }
                    case 4:
                        {
                            output.Save(sdf.FileName, ImageFormat.Emf);
                            break;
                        }
                    case 5:
                        {
                            output.Save(sdf.FileName, ImageFormat.Exif);
                            break;
                        }
                    case 6:
                        {
                            output.Save(sdf.FileName, ImageFormat.Gif);
                            break;
                        }
                    case 7:
                        {
                            output.Save(sdf.FileName, ImageFormat.Icon);
                            break;
                        }

                    case 8:
                        {
                            output.Save(sdf.FileName, ImageFormat.Tiff);
                            break;
                        }
                    case 9:
                        {
                            output.Save(sdf.FileName, ImageFormat.Wmf);
                            break;
                        }
                }
                MessageBox.Show("保存成功，位置：" + sdf.FileName);
            }
        }

        private void button4_Click(object sender, EventArgs e)
        {
            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "正在运行，请稍后……";
            Application.DoEvents();

            dt1 = DateTime.Now;

            Mat srcimg1 = Cv2.ImRead("test_img/frame11.png");
            Mat srcimg2 = Cv2.ImRead("test_img/frame12.png");

            Mat mid_img = Interpolate(srcimg1, srcimg2);

            dt2 = DateTime.Now;

            pictureBox2.Image = new Bitmap(mid_img.ToMemoryStream());

            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
            button2.Enabled = true;
        }
    }
}

下载

源码下载