cloud machine learning predict

问题

When I use prediction command of Google Cloud Machine Learning (https://cloud.google.com/ml/docs/quickstarts/prediction), I frequently get an error below:

$ gcloud beta ml predict --model=mnist --instances=data/predict_sample.tensor.json

ERROR: (gcloud.beta.ml.predict) HTTP request failed. Response: <!DOCTYPE html>
<html lang=en>
  <meta charset=utf-8>
  <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">
  <title>Error 502 (Server Error)!!1</title>
  <style>
    *{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:54px;width:150px}
  </style>
  <a href=//www.google.com/><span id=logo aria-label=Google></span></a>
  <p><b>502.</b> <ins>That’s an error.</ins>
  <p>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.  <ins>That’s all we know.</ins>

Is there anything that I can do to solve this error?

回答1:

Thanks for trying out Cloud ML. Since online prediction service is in alpha, there can be transient failures and actual response message might not be very helpful to the user. We are working towards making the error messages more actionable for the user.

In this particular case, server encountered some sort of internal error. Was the model deployment before this step successful? Also, were you able to see some 503 response code for predict calls immediately after deployment finished? 503 response code suggests that the service is still unavailable for use after deployment until the error goes away.

There is some chance, this is a problem with the model itself. I suggest that you use the script here, https://github.com/GoogleCloudPlatform/cloudml-samples/blob/master/mnist/deployable/local_predict.py to verify that the model can load and run locally. This will eliminate the possibility of a bad model. You might have to download the samples using the following:

curl -L -o cloudml-samples.zip https://github.com/GoogleCloudPlatform/cloudml-samples/archive/master.zip

You can run as follows:

python local_predict.py --model_dir=<model_dir>  data/predict_sample.tensor.json

Note that the model directory is where you have the "export.meta" and "export" files stored.

If this looks good, I will suggest retrying model deployment again to see if this was some kind of transient issue.

Hope this helps.

来源：https://stackoverflow.com/questions/40121254/cloud-machine-learning-predict

标签

tensorflow

google-cloud-ml