⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.
Jiang-Jia-Jun
commented
1 month ago
C# Release代码
opencv4.8版本 opencvsharp4.7 指定版本 cuda 12.1版本
运行时使用Cpu进行推理 RuntimeOption runtimeoption = new RuntimeOption(); runtimeoption.UseCpu(); fastdeploy.vision.detection.PPYOLOE model = new fastdeploy.vision.detection.PPYOLOE(model_file, params_file, config_file, runtimeoption, ModelFormat.PADDLE); if (!model.Initialized()) { Console.WriteLine("Failed to initialize.\n"); } Mat image = Cv2.ImRead(image_path); fastdeploy.vision.DetectionResult res = model.Predict(image); Console.WriteLine(res.ToString()); Mat res_img = fastdeploy.vision.Visualize.VisDetection(image, res, 0, 1, 0.5f); Cv2.ImShow("result.png", res_img); Cv2.WaitKey(0);
正常加载读取模型 运行到Predict推理，就异常闪退。调试后DetectionResult detection_result =ConvertResult.ConvertCResultToDetectionResult(fd_detection_result); 问题，可以检测到目标300个，然后在return后直接异常报错，包括下方的Visualize.VisDetection(image, res, 0, 1, 0.5f);中涉及到的反转换也都是异常，最后运行完结果
C#的exe程序不使用兼容模式的话应该直接到predict就闪退了，使用兼容模式能到最后结果显示，但是程序中的错误肯定还是如上面描述一样存在的，该如何处理