ARM BYOP (Bring Your Own Predict) VGG16 Demonstration

A demonstration of using Bring Your Own Predict (BYOP) deployed on ARM.

For details on adding ARM nodepools to a Wallaroo cluster, see Create ARM Nodepools for Kubernetes Clusters.

This tutorial can be downloaded as part of the Wallaroo Tutorials repository.

Arbitrary Python ARM Deployment Tutorial

This tutorial demonstrates how to use arbitrary python as a ML Model in Wallaroo. Arbitrary Python allows organizations to use Python scripts that require specific libraries and artifacts as models in the Wallaroo engine. This allows for highly flexible use of ML models with supporting scripts.

Arbitrary Python Script Requirements

The entry point of the arbitrary python aka BYOP (Bring Your Own Predict) model is any python script that must include the following.

  • class ImageClustering(Inference): The default inference class. This is used to perform the actual inferences. Wallaroo uses the _predict method to receive the inference data and call the appropriate functions for the inference.
    • def __init__: Used to initialize this class and load in any other classes or other required settings.
    • def expected_model_types: Used by Wallaroo to anticipate what model types are used by the script.
    • def model(self, model): Defines the model used for the inference. Accepts the model instance used in the inference.
      • self._raise_error_if_model_is_wrong_type(model): Returns the error if the wrong model type is used. This verifies that only the anticipated model type is used for the inference.
      • self._model = model: Sets the submitted model as the model for this class, provided _raise_error_if_model_is_wrong_type is not raised.
    • def _predict(self, input_data: InferenceData): This is the entry point for Wallaroo to perform the inference. This will receive the inference data, then perform whatever steps and return a dictionary of numpy arrays.
  • class ImageClusteringBuilder(InferenceBuilder): Loads the model and prepares it for inferencing.
    • def inference(self) -> ImageClustering: Sets the inference class being used for the inferences.
    • def create(self, config: CustomInferenceConfig) -> ImageClustering: Creates an inference subclass, assigning the model and any attributes required for it to function.

All other methods used for the functioning of these classes are optional, as long as they meet the requirements listed above.

Tutorial Prerequisites

  • Wallaroo Version 2023.2.1 or above instance.


Tutorial Steps

Import Libraries

The first step is to import the libraries we’ll be using. These are included by default in the Wallaroo instance’s JupyterHub service.

import numpy as np
import pandas as pd
import json
import os
import pickle
import pyarrow as pa
import tensorflow as tf
import wallaroo
from wallaroo.object import EntityNotFoundError

from sklearn.cluster import KMeans
from tensorflow.keras.datasets import cifar10
from tensorflow.keras import Model
from tensorflow.keras.layers import Flatten
from wallaroo.pipeline   import Pipeline
from wallaroo.deployment_config import DeploymentConfigBuilder
from wallaroo.framework import Framework

Open a Connection to Wallaroo

The next step is connect to Wallaroo through the Wallaroo client. The Python library is included in the Wallaroo install and available through the Jupyter Hub interface provided with your Wallaroo environment.

This is accomplished using the wallaroo.Client() command, which provides a URL to grant the SDK permission to your specific Wallaroo environment. When displayed, enter the URL into a browser and confirm permissions. Store the connection into a variable that can be referenced later.

If logging into the Wallaroo instance through the internal JupyterHub service, use wl = wallaroo.Client(). If logging in externally, update the wallarooPrefix and wallarooSuffix variables with the proper DNS information. For more information on Wallaroo DNS settings, see the Wallaroo DNS Integration Guide.

wl = wallaroo.Client()

Set Variables

We’ll set the name of our workspace, pipeline, models and files. Workspace names must be unique across the Wallaroo workspace. For this, we’ll add in a randomly generated 4 characters to the workspace name to prevent collisions with other users’ workspaces. If running this tutorial, we recommend hard coding the workspace name so it will function in the same workspace each time it’s run.

workspace_name = f'vgg16-clustering-workspace'
pipeline_name = f'vgg16-clustering-pipeline'

model_name = 'arm-vgg16-clustering'
model_file_name = './models/'

Create Workspace and Pipeline

We will now create the Wallaroo workspace to store our model and set it as the current workspace. Future commands will default to this workspace for pipeline creation, model uploads, etc. We’ll create our Wallaroo pipeline that is used to deploy our arbitrary Python model.

workspace = wl.get_workspace(name=workspace_name, create_if_not_exist=True)

pipeline = wl.build_pipeline(pipeline_name)

Upload Arbitrary Python Model

Arbitrary Python models are uploaded to Wallaroo through the Wallaroo Client upload_model method.

Upload Arbitrary Python Model Parameters

The following parameters are required for Arbitrary Python models. Note that while some fields are considered as optional for the upload_model method, they are required for proper uploading of a Arbitrary Python model to Wallaroo.

namestring (Required)The name of the model. Model names are unique per workspace. Models that are uploaded with the same name are assigned as a new version of the model.
pathstring (Required)The path to the model file being uploaded.
frameworkstring (Upload Method Optional, Arbitrary Python model Required)Set as Framework.CUSTOM.
input_schemapyarrow.lib.Schema (Upload Method Optional, Arbitrary Python model Required)The input schema in Apache Arrow schema format.
output_schemapyarrow.lib.Schema (Upload Method Optional, Arbitrary Python model Required)The output schema in Apache Arrow schema format.
convert_waitbool (Upload Method Optional, Arbitrary Python model Optional) (Default: True)
  • True: Waits in the script for the model conversion completion.
  • False: Proceeds with the script without waiting for the model conversion process to display complete.

Once the upload process starts, the model is containerized by the Wallaroo instance. This process may take up to 10 minutes.

Upload Arbitrary Python Model Return

The following is returned with a successful model upload and conversion.

namestringThe name of the model.
versionstringThe model version as a unique UUID.
file_namestringThe file name of the model as stored in Wallaroo.
image_pathstringThe image used to deploy the model in the Wallaroo engine.
last_update_timeDateTimeWhen the model was last updated.

For our example, we’ll start with setting the input_schema and output_schema that is expected by our ImageClustering._predict() method.

input_schema = pa.schema([
    pa.field('images', pa.list_(

output_schema = pa.schema([
    pa.field('predictions', pa.int64()),

Upload Model

Now we’ll upload our model. The framework is Framework.CUSTOM for arbitrary Python models, and we’ll specify the input and output schemas for the upload.

An important note for the ARM version of the VGG16 model is verifying that the Python modules used will operate in an ARM environment. For example, the x86 model has the following as its requirements.txt:


The ARM version replaces the tensorflow module with the tensorflow-aarch64 that runs in the ARM archtecture. Otherwise, the model and Python script is the same.


Note that during the upload, the arch setting is wallaroo.engine_config.Architecture.ARM.

from wallaroo.engine_config import Architecture

model = wl.upload_model(model_name, 
Waiting for model loading - this will take up to 10.0min.
Model is pending loading to a container runtime..
Model is attempting loading to a container runtime.......................successful


Updated At2023-18-Sep 14:59:39
{'name': 'arm-vgg16-clustering', 'version': '14f9929d-cb37-4e44-aacd-2120b349ef31', 'file_name': '', 'image_path': '', 'last_update_time': datetime.datetime(2023, 9, 18, 14, 59, 39, 729445, tzinfo=tzutc())}

Deploy Pipeline

The model is uploaded and ready for use. We’ll add it as a step in our pipeline, then deploy the pipeline. For this example we’re allocated 0.25 cpu and 4 Gi RAM to the pipeline through the pipeline’s deployment configuration.

The deployment configuration inherits its Architecture setting from the model, so it will automatically be set for ARM processors.

created2023-09-18 14:57:31.537378+00:00
last_updated2023-09-18 14:57:31.537378+00:00
deployment_config = DeploymentConfigBuilder() \
    .cpus(1).memory('4Gi') \

Waiting for deployment - this will take up to 90s ........................ ok

{‘status’: ‘Running’,
‘details’: [],
’engines’: [{‘ip’: ‘’,
’name’: ’engine-d665b9c7d-jhr7s’,
‘status’: ‘Running’,
‘reason’: None,
‘details’: [],
‘pipeline_statuses’: {‘pipelines’: [{‘id’: ‘vgg16-clustering-pipeline’,
‘status’: ‘Running’}]},
‘model_statuses’: {‘models’: [{’name’: ‘arm-vgg16-clustering’,
‘version’: ‘14f9929d-cb37-4e44-aacd-2120b349ef31’,
‘sha’: ’e53d1775766567eda5fd7ecb1618ea073fc18ffd6298c75da67be3b704029f15’,
‘status’: ‘Running’}]}}],
’engine_lbs’: [{‘ip’: ‘’,
’name’: ’engine-lb-584f54c899-ksj6c’,
‘status’: ‘Running’,
‘reason’: None,
‘details’: []}],
‘sidekicks’: [{‘ip’: ‘’,
’name’: ’engine-sidekick-arm-vgg16-clustering-2-6f5975c9f6-6dgct’,
‘status’: ‘Running’,
‘reason’: None,
‘details’: [],
‘statuses’: ‘\n’}]}

Run inference

Everything is in place - we’ll now run a sample inference with some toy data. In this case we’re randomly generating some values in the data shape the model expects, then submitting an inference request through our deployed pipeline.

input_data = {
        "images": [np.random.randint(0, 256, (32, 32, 3), dtype=np.uint8)] * 2,
dataframe = pd.DataFrame(input_data)
0[[[142, 30, 10], [182, 46, 219], [233, 142, 22...
1[[[142, 30, 10], [182, 46, 219], [233, 142, 22...
pipeline.infer(dataframe, timeout=10000)
02023-09-18 15:00:07.019[142, 30, 10, 182, 46, 219, 233, 142, 223, 94,...10
12023-09-18 15:00:07.019[142, 30, 10, 182, 46, 219, 233, 142, 223, 94,...10

Undeploy Pipelines

The inference is successful, so we will undeploy the pipeline and return the resources back to the cluster.

Waiting for undeployment - this will take up to 45s .................................... ok
created2023-09-18 14:57:31.537378+00:00
last_updated2023-09-18 14:59:40.816423+00:00
versions65299c7d-79dd-477e-b54e-adb0239f60eb, d42d5272-86dd-414b-8928-6dea07c866c1