Merge branch 'master' of https://github.com/ivilson/Yolov7net

Author: iwaitu

README.md

@@ -24,9 +24,15 @@ work on i13900k + 64Gb Ram + RTX4090
 ![](https://raw.githubusercontent.com/ivilson/Yolov7net/master/performance.png)
 
 
+![](https://raw.githubusercontent.com/ivilson/Yolov7net/master/test/Yolov7net.test/Assets/demo.jpg)
 
 ### 2024.6.9
-1. add yolov10 support.
+
+Usage:
+
+1. install-package IVilson.AI.Yolov7net
+2. [Program.cs](https://github.com/ivilson/Yolov7net/blob/master/Yolov7net.Demo/Program.cs)
+3. add yolov10 support.
 Yolov10
 ```csharp
 // init Yolov8 with onnx (include nms results)file path
@@ -66,6 +72,10 @@ foreach (var prediction in predictions) // 迭代预测结果并绘制
     canvas.DrawText($"{prediction.Label.Name} ({score})", x, y, paintText);
 }
 ```
+
+
+![](https://raw.githubusercontent.com/ivilson/Yolov7net/master/result.jpg)
+
 yolov10 和 yolov7 保持兼容，包含了NMS 操作，感觉性能上比不上yolov9
 
 
@@ -88,8 +98,6 @@ The net8.0 branch has been renamed to master. This is now the main branch where
 
 
 
-
-
 # Yolov7net Now support yolov9,yolov8,yolov7,yolov5.
 
 .net 6 yolov5, yolov7, yolov8 onnx runtime interface, work for:
@@ -99,104 +107,10 @@ The net8.0 branch has been renamed to master. This is now the main branch where
 4. yolov5 https://github.com/ultralytics/yolov5
 
 
-Usage:
 
-install-package IVilson.AI.Yolov7net
 
-![](https://raw.githubusercontent.com/ivilson/Yolov7net/master/test/Yolov7net.test/Assets/demo.jpg)
 
-yolov9 和 yolov8 的 onnx 输出参数相同，都是 (1,84,8400)
 
-如果有问题请前往 issus 进行提问，我会尽量解答
-
-Yolov9
-```csharp
-// init Yolov8 with onnx (include nms results)file path
-using var yolo = new Yolov8("./assets/yolov9-c.onnx", true);
-// setup labels of onnx model 
-yolo.SetupYoloDefaultLabels();   // use custom trained model should use your labels like: yolo.SetupLabels(string[] labels)
-using var image = Image.FromFile("Assets/demo.jpg");
-var predictions = yolo.Predict(image);  // now you can use numsharp to parse output data like this : var ret = yolo.Predict(image,useNumpy:true);
-// draw box
-using var graphics = Graphics.FromImage(image);
-foreach (var prediction in predictions) // iterate predictions to draw results
-{
-    double score = Math.Round(prediction.Score, 2);
-    graphics.DrawRectangles(new Pen(prediction.Label.Color, 1),new[] { prediction.Rectangle });
-    var (x, y) = (prediction.Rectangle.X - 3, prediction.Rectangle.Y - 23);
-    graphics.DrawString($"{prediction.Label.Name} ({score})",
-                    new Font("Consolas", 16, GraphicsUnit.Pixel), new SolidBrush(prediction.Label.Color),
-                    new PointF(x, y));
-}
-```
-
-Yolov8
-```csharp
-// init Yolov8 with onnx (include nms results)file path
-using var yolo = new Yolov8("./assets/yolov8n.onnx", true);
-// setup labels of onnx model 
-yolo.SetupYoloDefaultLabels();   // use custom trained model should use your labels like: yolo.SetupLabels(string[] labels)
-using var image = Image.FromFile("Assets/demo.jpg");
-var predictions = yolo.Predict(image);  // now you can use numsharp to parse output data like this : var ret = yolo.Predict(image,useNumpy:true);
-// draw box
-using var graphics = Graphics.FromImage(image);
-foreach (var prediction in predictions) // iterate predictions to draw results
-{
-    double score = Math.Round(prediction.Score, 2);
-    graphics.DrawRectangles(new Pen(prediction.Label.Color, 1),new[] { prediction.Rectangle });
-    var (x, y) = (prediction.Rectangle.X - 3, prediction.Rectangle.Y - 23);
-    graphics.DrawString($"{prediction.Label.Name} ({score})",
-                    new Font("Consolas", 16, GraphicsUnit.Pixel), new SolidBrush(prediction.Label.Color),
-                    new PointF(x, y));
-}
-```
-yolov7 可以直接导出包含nms操作结果的onnx， 使用方法略有不同，需要使用 Yolov7 这个类
-
-```csharp
-// init Yolov7 with onnx (include nms results)file path
-using var yolo = new Yolov7("./assets/yolov7-tiny_640x640.onnx", true);
-// setup labels of onnx model 
-yolo.SetupYoloDefaultLabels();   // use custom trained model should use your labels like: yolo.SetupLabels(string[] labels)
-using var image = Image.FromFile("Assets/demo.jpg");
-var predictions = yolo.Predict(image);
-
-// draw box
-using var graphics = Graphics.FromImage(image);
-foreach (var prediction in predictions) // iterate predictions to draw results
-{
-    double score = Math.Round(prediction.Score, 2);
-    graphics.DrawRectangles(new Pen(prediction.Label.Color, 1),new[] { prediction.Rectangle });
-    var (x, y) = (prediction.Rectangle.X - 3, prediction.Rectangle.Y - 23);
-    graphics.DrawString($"{prediction.Label.Name} ({score})",
-                    new Font("Consolas", 16, GraphicsUnit.Pixel), new SolidBrush(prediction.Label.Color),
-                    new PointF(x, y));
-}
-```
-
-对于未包括nms 结果的模型，需要用到 yolov5 这个类
-```csharp
-// init Yolov5 with onnx file path
-using var yolo = new Yolov5("./assets/yolov7-tiny_640x640.onnx", true);
-// setup labels of onnx model 
-yolo.SetupYoloDefaultLabels();   // use custom trained model should use your labels like: yolo.SetupLabels(string[] labels)
-using var image = Image.FromFile("Assets/demo.jpg");
-var predictions = yolo.Predict(image);
-
-// draw box
-using var graphics = Graphics.FromImage(image);
-foreach (var prediction in predictions) // iterate predictions to draw results
-{
-    double score = Math.Round(prediction.Score, 2);
-    graphics.DrawRectangles(new Pen(prediction.Label.Color, 1),new[] { prediction.Rectangle });
-    var (x, y) = (prediction.Rectangle.X - 3, prediction.Rectangle.Y - 23);
-    graphics.DrawString($"{prediction.Label.Name} ({score})",
-                    new Font("Consolas", 16, GraphicsUnit.Pixel), new SolidBrush(prediction.Label.Color),
-                    new PointF(x, y));
-}
-
-
-```
-![](https://raw.githubusercontent.com/ivilson/Yolov7net/master/result.jpg)
 
 # References & Acknowledgements