Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

[Failed] Cannot execute sklearn-iris-predictor-default

See original GitHub issue

/kind bug

What steps did you take and what happened: Cannot execute sklearn-iris-predictor-default

After booting kfserving from istio, I do following commands

kubectl label namespace/default serving.kubeflow.org/inferenceservice=enabled
kubectl apply -f docs/samples/sklearn/sklearn.yaml

I cannot solve this problem even checking KFSERVING_DEBUG_GUIDE.md

What did you expect to happen: sklearn works fine.

Anything else you would like to add:

$ kubectl get ksvc
NAME                              URL                                                          LATESTCREATED                           LATESTREADY   READY     REASON
sklearn-iris-predictor-default    http://sklearn-iris-predictor-default.default.example.com    sklearn-iris-predictor-default-tmrq6                  Unknown   RevisionMissing

$ kubectl get revision $(kubectl get configuration sklearn-iris-predictor-default --output jsonpath="{.status.latestCreatedRevisionName}")
NAME                                   CONFIG NAME                      K8S SERVICE NAME                       GENERATION   READY     REASON
sklearn-iris-predictor-default-tmrq6   sklearn-iris-predictor-default   sklearn-iris-predictor-default-tmrq6   1            Unknown

$ kubectl get pods -A | grep kfserving
istio-system      kfserving-ingressgateway-64c7bd9b76-4v9m8                      1/1     Running     0          122m
kubeflow          kfserving-controller-manager-0                                 2/2     Running     1          119m

Environment:

Istio Version:1.0.2
Knative Version:on Istio
KFServing Version:on Istio
Kubeflow version:on Istio
Kfdef:k8s_istio
Microk8s:1.15.11
Kubernetes version: (use kubectl version):1.15.11
OS (e.g. from /etc/os-release):Ubuntu 19.10

Issue Analytics

State:
Created 3 years ago
Comments:14 (7 by maintainers)

Top GitHub Comments

1reaction

yuzisuncommented, May 22, 2020

@sakaia looks similar to this issue https://github.com/ubuntu/microk8s/issues/784 ?

1reaction

k8s-ci-robotcommented, May 22, 2020

@sakaia: The label(s) kind/example cannot be applied, because the repository doesn’t have them

In response to this:

/kind example

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

Top Results From Across the Web

[Failed] Cannot execute sklearn-iris-predictor-default #839

After executing kubectl apply , some pods are running but dissapearing. So I reexecute it and get following message. $ kubectl describe pods ......

Debugging guide - KServe Documentation Website

Go through this step by step guide to understand what failed. kubectl get inferenceservices sklearn-iris NAME URL READY DEFAULT TRAFFIC CANARY TRAFFIC AGE ......

Kfserving Example Issue -- failed quota: kf-resource-quota ...

I installed KFserving together with Kubeflow on my k8s cluster, but when I tried to run the Sklearn example provided here ...

sklearn.ensemble.AdaBoostClassifier

An AdaBoost regressor that begins by fitting a regressor on the original dataset and then fits additional copies of the regressor on the...

6.1. Pipelines and composite estimators - Scikit-learn

Pipelines help avoid leaking statistics from your test data into the trained model in cross-validation, by ensuring that the same samples are used...