通过REST调用CloudML Predict时遇到内部错误

通过REST调用CloudML Predict时遇到内部错误,rest,google-app-engine,google-cloud-ml,google-cloud-ml-engine,Rest,Google App Engine,Google Cloud Ml,Google Cloud Ml Engine,我的应用程序正在GAE中运行。此应用程序对我的CloudML进行REST调用 这是代码 GoogleCredential credential = GoogleCredential.getApplicationDefault() .createScoped(Collections.singleton(CLOUDML_SCOPE)); HttpTransport httpTransport = GoogleNetHttpTranspo

我的应用程序正在GAE中运行。此应用程序对我的CloudML进行REST调用

这是代码

        GoogleCredential credential = GoogleCredential.getApplicationDefault()
                .createScoped(Collections.singleton(CLOUDML_SCOPE));
        HttpTransport httpTransport = GoogleNetHttpTransport.newTrustedTransport();
        HttpRequestInitializer requestInitializer = request -> {
            credential.initialize(request);
            request.setReadTimeout(0);
        };

        HttpRequestFactory requestFactory = httpTransport.createRequestFactory(
                requestInitializer);

        GenericUrl url = new GenericUrl(predictRestUrl);

        JacksonFactory jacksonFactory = new JacksonFactory();
        JsonHttpContent jsonHttpContent = new JsonHttpContent(jacksonFactory, getPayLoad());

        ByteArrayOutputStream baos = new ByteArrayOutputStream();

        jsonHttpContent.setWrapperKey("instances");
        jsonHttpContent.writeTo(baos);
        LOG.info("Executing request... " + baos.toString());
        HttpRequest request = requestFactory.buildPostRequest(url, jsonHttpContent);

        HttpResponse response = request.execute();
我已将ReadTimeOut设置为0,因为我经常遇到读取超时异常

现在有了这段代码,我经常从CloudML得到下面的错误响应

com.google.api.client.http.HttpResponseException: 500 Internal Server Error
{
  "error": {
    "code": 500,
    "message": "Internal error encountered.",
    "errors": [
      {
        "message": "Internal error encountered.",
        "domain": "global",
        "reason": "backendError"
      }
    ],
    "status": "INTERNAL"
  }
}

在哪里可以获取REST调用CloudML的日志?如何进一步调试?

我们与@sag合作,确定500错误是由于长时间“冷启动”导致的超时。如果您有一段时间没有向您的模型发送流量,或者如果您发送的流量足够多,我们需要启动更多实例,那么您将遇到“冷启动”,其中一个或多个实例启动。目前,这可能是一个漫长的过程,有时我们会超时,并可能导致500个错误

可以安全地重试这些错误;我们建议使用指数退避