http调用速度慢

2019-01-15 02:01:23 317 阅读 AI 写同款 · GEO 优化AI 选题数据监测一键分发 ›

RK3588上从零部署Facenet人脸识别：PyTorch转ONNX再到RKNN的完整避坑指南本文提供了在RK3588开发板上从零部署Facenet人脸识别模型的完整指南。详细介绍了从PyTorch模型导出、转换为ONNX格式，再通过RKNN-Toolkit2转换为RKNN格式的完整流程，并重点分享了环境配置、算子兼容性处理、量化调优及板端部署中的关键步骤与避坑经验。阅读详情

string htp = "https://api.weixin.qq.com/cgi-bin/message/template/send?access_token=" + access_token;
jsonfh = HttpPost(htp, jsonText);

如果本地调用速度很快，但是放到服务器上，调用需要15秒才能返回结果

public static string HttpPost(string url, string postData)
{
ServicePointManager.ServerCertificateValidationCallback += RemoteCertificateValidate;
byte[] data = Encoding.UTF8.GetBytes(postData);
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
request.Proxy = null;
request.Method = "Post";
request.ContentType = "application/json";
request.ContentLength = data.Length;
request.KeepAlive = true;

Stream stream = request.GetRequestStream();
stream.Write(data, 0, data.Length);

HttpWebResponse response;
try
{
response = (HttpWebResponse)request.GetResponse();
}
catch (WebException ex)
{
response = (HttpWebResponse)ex.Response;
}

StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8);
string content = reader.ReadToEnd();

request.Abort();
response.Close();
reader.Dispose();
stream.Close();
stream.Dispose();

return content;
}

...全文