Batch Prediction Jobs

Pre-requisites

MinIO should already be installed with Seldon Enterprise Platform. The MinIO browser should be exposed on /minio/ (note the trailing forward slash).

For trials, the credentials will by default be the same as the Enterprise Platform login, with MinIO using the email as its Access Key and the password as its Secret Key.

Other cloud storage services, such as S3 and GCS, can be specified alternatively with the corresponding secret files configured.

On a production cluster, the namespace needs to have been set up with a service account. This can be found under the argo install documentation.

This demo helps you learn about:

• Deploying a deployment with a pre trained SKlearn iris model

• Running a batch job to get predictions

• Checking the output

Create a Deployment

1. Click on Create new deployment button.

2. Enter the deployment details as follows:

   • Name: batch-demo

   • Namespace: seldon

   • Type: Seldon Deployment

   

   deployment wizard details step
3. Configure the default predictor as follows:

   • Runtime: Scikit Learn

   • Model URI: gs://seldon-models/scv2/samples/mlserver_1.6.0/iris-sklearn

   • Model Project: default

   • Storage Secret: (leave blank/none)

   • Model Name: iris

The Model Name is linked to the name described in the model-settings.json file, located in the Google Cloud Storage location. Changing the name in the JSON file would also require changing the Model Name, and vice versa.

1. Skip Next for the remaining steps, then click Launch.

2. If your deployment is launched successfully, it will have Available status, on the overview page.

Setup Input Data

1. Download the input data file iris-input.txt.

15KB

iris-input.txt

Open

The first few lines of the input file `iris-input.txt` should show the following format:

{"inputs":[{"name":"predict","data":[0.38606369295833043,0.006894049558299753,0.6104082981607108,0.3958954239450676],"datatype":"FP64","shape":[1,4]}]}
{"inputs":[{"name":"predict","data":[0.7223678219956075,0.608521741883582,0.8596266157372878,0.20041864827775757],"datatype":"FP64","shape":[1,4]}]}
{"inputs":[{"name":"predict","data":[0.8659159480026418,0.2383384971368594,0.7743518759043038,0.8748919374334038],"datatype":"FP64","shape":[1,4]}]}

1. Go to the MinIO browser and use the button in the bottom-right to create a bucket. Call it data.

2. Again from the bottom-right choose to upload the iris-input.txt file to the data bucket.

Run a Batch Job

1. Click the new deployment batch-demo in the Overview page.

2. Click the Batch Jobs in the left pane.

3. Click Create Your First Job, enter the following details, and click Submit:

   • Input Data Location: minio://data/iris-input.txt

   • Output Data Location: minio://data/iris-output-{{workflow.name}}.txt

   • Number of Workers: 5

   • Number of Retries: 3

   • Batch Size: 10

   • Minimum Batch Wait Interval (sec) : 0

   • Method: Predict

   • Transport Protocol: REST

   • Input Data Type: Open Inference Protocol (OIP)

   • Object Store Secret Name: minio-bucket-envvars

   Note: In this job minio-bucket-envvars is a pre-created secret in the same namespace as the model, containing environment variables.

In the Resources (Optional) section, you can specify how much memory and CPU are allocated to the containers in this specific batch job workflow. If no values are set on this form, the default values specified in Helm values will be used. Refer to the Kubernetes documentation on requests and limits for details.

4. Give the job a couple of minutes to complete, then refresh the page to see the status.

Expand to see batch job status

5. Inspect the output file in MinIO:

miniooutput

If you open that file you should see contents such as:

{"model_name":"","outputs":[{"data":[0],"name":"predict","shape":[1],"datatype":"INT64"}],"parameters":{"batch_index":0}}
{"model_name":"","outputs":[{"data":[0],"name":"predict","shape":[1],"datatype":"INT64"}],"parameters":{"batch_index":2}}
{"model_name":"","outputs":[{"data":[1],"name":"predict","shape":[1],"datatype":"INT64"}],"parameters":{"batch_index":4}}
{"model_name":"","outputs":[{"data":[0],"name":"predict","shape":[1],"datatype":"INT64"}],"parameters":{"batch_index":1}}

If not, see the argo section for troubleshooting.