Stack Overflow
Stack Overflow

Questions tagged [seldon]

34 questions
5
votes
1 answer

Internal error occurred: failed calling webhook "v1.vseldondeployment.kb.io" while deploying Seldon yaml file on minikube

I am trying to follow the instruction on Seldon to build and deploy the iris model on minikube. https://docs.seldon.io/projects/seldon-core/en/latest/workflow/github-readme.html#getting-started I am able to install Seldon with Helm and Knative using…
Titus Fong
  • 51
  • 1
5
votes
2 answers

Seldon: How to Use My Own Grafana and Prometheus Instances?

I want to use my already existing Prometheus and Grafana instances in the monitoring namespace to emulate what seldon-core-analytics is doing. I'm using the prometheus community helm charts and installed kube-prometheus-stack on k8s. Here's what…
Riley Hun
  • 2,541
  • 5
  • 31
  • 77
3
votes
1 answer

How to seldon-core quick-start on kind with port-forward?

Following the documentation I try to setup the Seldon-Core quick-start https://docs.seldon.io/projects/seldon-core/en/v1.11.1/workflow/github-readme.html I don't have LoadBalancer so I would like to use port-fowarding for accessing to the service. I…
ucsky
  • 442
  • 6
  • 13
3
votes
1 answer

Why are there two services for one seldon deployment

I noticed whenever I deployed one model, there are two services, e.g. kubectl get service -n model-namespace NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE iris-model-default ClusterIP …
zyxue
  • 7,904
  • 5
  • 48
  • 74
3
votes
2 answers

ML Model pod keeps restarting in Seldon deployment

I have a Seldon deployment like this: apiVersion: machinelearning.seldon.io/v1alpha2 kind: SeldonDeployment metadata: name: mlflow spec: name: wines predictors: - graph: children: [] implementation: MLFLOW_SERVER …
Israel Varea
  • 2,600
  • 2
  • 17
  • 24
2
votes
1 answer

Route the output of model A as the input of model B on Seldon Core

I'm testing Seldon Core and am wondering if there is an easy way to route the output of model A as the input of model B on Seldon Core. What would be the best practice?
user3368526
  • 2,168
  • 10
  • 37
  • 52
1
vote
1 answer

can configurable declarative Horizontal Pod AutoScaler (HPA) in seldon deployment (CRD) for multiple deployment environment is possible?

Using CRD of SeldonDeployment I want to configure HPA following this example . The seldon deployment config is - apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: seldon-model spec: name: test-deployment …
M.A.K. Simanto
  • 634
  • 1
  • 7
  • 20
1
vote
1 answer

Attribute Error : pickle.load() Seldon Deployment

I am doing a seldon deployment. I have created custom pipelines using sklearn and it is in the directory MyPipelines/CustomPipelines.py. The main code ie. my_prediction.py is the file which seldon will execute by default (based on my configuration).…
Chaitanya Patil
  • 183
  • 2
  • 16
1
vote
1 answer

Seldon Core Loading sklearn/irir failed

I tried to load the iris model using seldon core, and unfortunately the following error occurred. SKLEARN_SERVER loads seldon’s sklearn/iris model with the following error. starting microservice 2021-09-02 02:43:19,363 -…
xm lian
  • 73
  • 13
1
vote
0 answers

Can I deploy PyTorch trained models on Seldon?

I have tried deploying PyTorch model on seldon by using TRITON server. with yaml apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: cifar10 spec: annotations: seldon.io/engine-seldon-log-messages-externally:…
Nikhil Khandelwal
  • 11
  • 1
1
vote
1 answer

SeldonIO | sklearn_iris and sklearn_spacy_text | not working in k8s

Ref: https://github.com/SeldonIO/seldon-core/blob/master/examples/models/sklearn_iris/sklearn_iris.ipynb https://github.com/SeldonIO/seldon-core/tree/master/examples/models/sklearn_spacy_text #Steps Done 1. kubectl port-forward $(kubectl get pods -l…
Antony Johnson
  • 41
  • 6
1
vote
1 answer

failed calling webhook "v1.vseldondeployment.kb.io". x509: certificate signed by unknown authority

I am trying Seldon Core example. Here's SeldonExampleDeployment.yaml. apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: seldon-model spec: name: test-deployment predictors: - componentSpecs: - spec: …
Anderson
  • 3,139
  • 3
  • 33
  • 45
1
vote
0 answers

Is it possible to determine model input at runtime with seldon

I'm thinking of deploying ml models with seldon core on kubernetes. Seldon provides ways to do pre-processing, post-processing, predicting, combining and routing models. But, I think, these all assume that the input data is fixed. Is the input data…
Pieter
  • 3,262
  • 1
  • 17
  • 27
1
vote
1 answer

Does the Seldon SKLearn Server support SVC models?

I am trying to deploy a Seldon Deployment with a Sklearn Model. The model is a SVC classifier. apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: test-model namespace: model-dev spec: name: anomaly-ml …
user3166312
  • 11
  • 1
1
vote
1 answer

How to Get Seldon Sklearn servers to work with Google Cloud Storage from GKE

Needed to understand how to make seldon work with prepackaged python pickles and servers. After following instructions from seldonio site for sklearn server, am still unable to get the predefined server models to work. I have the iris model placed…
user636191
  • 21
  • 1
1
2 3