I am trying to create a custom prediction routine on GCP AI-Platform using scikit-learn by following along the AI Platform tutorial.
When I get to the end Deploy your custom prediction routine, I create the model on the global endpoint as stated
gcloud ai-platform models create $MODEL_NAME \
--regions us-central1
However, I cannot use gcloud beta ai-platform versions create to create a model version. When I follow the next step:
gcloud components install beta
gcloud beta ai-platform versions create $VERSION_NAME \
--model $MODEL_NAME \
--runtime-version 2.1 \
--python-version 3.7 \
--origin gs://$BUCKET_NAME/custom_prediction_routine_tutorial/model/ \
--package-uris gs://$BUCKET_NAME/custom_prediction_routine_tutorial/my_custom_code-0.1.tar.gz \
--prediction-class predictor.MyPredictor
I get the following cryptic error (presumably meaning it cant find the model resource):
Using endpoint [https://us-central-ml.googleapis.com/]
ERROR: (gcloud.beta.ai-platform.versions.create) HTTPError 404: <!DOCTYPE html>
<html lang=en>
<meta charset=utf-8>
<meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">
<title>Error 404 (Not Found)!!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>404.</b> <ins>That’s an error.</ins>
<p>The requested URL <code>/v1/projects/test-project/models/IrisPredictor/versions</code> was not found on this server. <ins>That’s all we know.</ins>
Note that I have changed the python version from 3.5 -> 3.7 and runtime version from 1.13 -> 2.1 from the tutorial since that does work when I go to the gcp console in the browser and create a new version manually and using python 3.5 is not an option for me.
You should add the --region global flag to the command.
Also keep in mind that you can only deploy a custom prediction routine when you use a legacy (MLS1) machine type for your model version.
To specify the machine-type, you can pick between mls1-c1-m2 and mls1-c4-m2. For more information about the machine types read this doc