目录
说明
效果
编辑模型信息
det_face.onnx
gazelle_dinov2_vitl14_inout_1x3x448x448_1xNx4.onnx
项目
代码
下载
参考
说明
github地址：https://github.com/fkryan/gazelle
This is the official implementation for Gaze-LLE, a transformer approach for estimating gaze targets that leverages the power of pretrained visual foundation models. Gaze-LLE provides a streamlined gaze architecture that learns only a lightweight gaze decoder on top of a frozen, pretrained visual encoder (DINOv2). Gaze-LLE learns 1-2 orders of magnitude fewer parameters than prior works and doesn't require any extra input modalities like depth and pose!
效果
模型信息
det_face.onnx
Model Properties
-------------------------
---------------------------------------------------------------
Inputs
-------------------------
name：input.1
tensor：Float[1, 3, -1, -1]
---------------------------------------------------------------
Outputs
-------------------------
name：448
tensor：Float[12800, 1]
name：471
tensor：Float[3200, 1]
name：494
tensor：Float[800, 1]
name：451
tensor：Float[12800, 4]
name：474
tensor：Float[3200, 4]
name：497
tensor：Float[800, 4]
name：454
tensor：Float[12800, 10]
name：477
tensor：Float[3200, 10]
name：500
tensor：Float[800, 10]
---------------------------------------------------------------
gazelle_dinov2_vitl14_inout_1x3x448x448_1xNx4.onnx
Model Properties
-------------------------
---------------------------------------------------------------
Inputs
-------------------------
name：image_bgr
tensor：Float[1, 3, 448, 448]
name：bboxes_x1y1x2y2
tensor：Float[1, -1, 4]
---------------------------------------------------------------
Outputs
-------------------------
name：heatmap
tensor：Float[-1, 64, 64]
name：inout
tensor：Float[-1]
---------------------------------------------------------------
项目
代码
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.Windows.Forms;
namespace Onnx_Demo
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}
string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
string image_path = "";
DateTime dt1 = DateTime.Now;
DateTime dt2 = DateTime.Now;
Mat image;
Mat result_image;
FaceDet face_det;
GazeLLE gazelle;
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;
}
private void button2_Click(object sender, EventArgs e)
{
if (image_path == "")
{
return;
}
button2.Enabled = false;
Application.DoEvents();
image = new Mat(image_path);
result_image = image.Clone();
dt1 = DateTime.Now;
List<Bbox> head_boxes = face_det.Detect(image);
foreach (var item in head_boxes)
{
Rect rect = Rect.FromLTRB((int)item.xmin, (int)item.ymin, (int)item.xmax, (int)item.ymax);
Cv2.Rectangle(result_image, rect, Scalar.Red);
}
List<Mat> resized_heatmaps = gazelle.Predict(image, head_boxes);
dt2 = DateTime.Now;
DrawGaze(result_image, head_boxes, resized_heatmaps);
pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
button2.Enabled = true;
}
void DrawGaze(Mat frame, List<Bbox> head_boxes, List<Mat> heatmaps, float thr = 0.0f)
{
int num_box = head_boxes.Count;
for (int i = 0; i < num_box; i++)
{
double max_score;
OpenCvSharp.Point classIdPoint;
double minVal;
OpenCvSharp.Point minLoc;
Cv2.MinMaxLoc(heatmaps[i], out minVal, out max_score, out minLoc, out classIdPoint);
int cx = classIdPoint.X;
int cy = classIdPoint.Y;
if (max_score >= thr)
{
int head_cx = (int)((head_boxes[i].xmin + head_boxes[i].xmax) * 0.5);
int head_cy = (int)((head_boxes[i].ymin + head_boxes[i].ymax) * 0.5);
Cv2.ArrowedLine(frame, new OpenCvSharp.Point(head_cx, head_cy), new OpenCvSharp.Point(cx, cy), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);
}
}
}
private void Form1_Load(object sender, EventArgs e)
{
face_det = new FaceDet("model\\det_face.onnx");
gazelle = new GazeLLE("model\\gazelle_dinov2_vitl14_inout_1x3x448x448_1xNx4.onnx");
image_path = "test_img\\1.jpg";
pictureBox1.Image = new Bitmap(image_path);
}
private void button3_Click(object sender, EventArgs e)
{
if (pictureBox2.Image == null)
{
return;
}
Bitmap output = new Bitmap(pictureBox2.Image);
SaveFileDialog sdf = new SaveFileDialog();
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);
}
}
}
}
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.Windows.Forms;namespace Onnx_Demo
{public partial class Form1 : Form{public Form1(){InitializeComponent();}string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";string image_path = "";DateTime dt1 = DateTime.Now;DateTime dt2 = DateTime.Now;Mat image;Mat result_image;FaceDet face_det;GazeLLE gazelle;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;}private void button2_Click(object sender, EventArgs e){if (image_path == ""){return;}button2.Enabled = false;Application.DoEvents();image = new Mat(image_path);result_image = image.Clone();dt1 = DateTime.Now;List<Bbox> head_boxes = face_det.Detect(image);foreach (var item in head_boxes){Rect rect = Rect.FromLTRB((int)item.xmin, (int)item.ymin, (int)item.xmax, (int)item.ymax);Cv2.Rectangle(result_image, rect, Scalar.Red);}List<Mat> resized_heatmaps = gazelle.Predict(image, head_boxes);dt2 = DateTime.Now;DrawGaze(result_image, head_boxes, resized_heatmaps);pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";button2.Enabled = true;}void DrawGaze(Mat frame, List<Bbox> head_boxes, List<Mat> heatmaps, float thr = 0.0f){int num_box = head_boxes.Count;for (int i = 0; i < num_box; i++){double max_score;OpenCvSharp.Point classIdPoint;double minVal;OpenCvSharp.Point minLoc;Cv2.MinMaxLoc(heatmaps[i], out minVal, out max_score, out minLoc, out classIdPoint);int cx = classIdPoint.X;int cy = classIdPoint.Y;if (max_score >= thr){int head_cx = (int)((head_boxes[i].xmin + head_boxes[i].xmax) * 0.5);int head_cy = (int)((head_boxes[i].ymin + head_boxes[i].ymax) * 0.5);Cv2.ArrowedLine(frame, new OpenCvSharp.Point(head_cx, head_cy), new OpenCvSharp.Point(cx, cy), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);}}}private void Form1_Load(object sender, EventArgs e){face_det = new FaceDet("model\\det_face.onnx");gazelle = new GazeLLE("model\\gazelle_dinov2_vitl14_inout_1x3x448x448_1xNx4.onnx");image_path = "test_img\\1.jpg";pictureBox1.Image = new Bitmap(image_path);}private void button3_Click(object sender, EventArgs e){if (pictureBox2.Image == null){return;}Bitmap output = new Bitmap(pictureBox2.Image);SaveFileDialog sdf = new SaveFileDialog();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);}}}
}
下载
源码下载
参考
https://github.com/hpc203/Gaze-LLE-onnxrun
