Wallaroo SDK Upload Arbitrary Python Tutorial: Deploy VGG16 Model

How to deploy a VGG166 model as a arbitrary python model in Wallaroo.

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

Arbitrary Python Tutorial Deploy Model in Wallaroo Upload and Deploy

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.

Tutorial Goals

This tutorial is split into two parts:

  • Wallaroo SDK Upload Arbitrary Python Tutorial: Generate Model: Train a dummy KMeans model for clustering images using a pre-trained VGG16 model on cifar10 as a feature extractor. The Python entry points used for Wallaroo deployment will be added and described.
    • A copy of the arbitrary Python model models/model-auto-conversion-BYOP-vgg16-clustering.zip is included in this tutorial, so this step can be skipped.
  • Arbitrary Python Tutorial Deploy Model in Wallaroo Upload and Deploy: Deploys the KMeans model in an arbitrary Python package in Wallaroo, and perform sample inferences. The file models/model-auto-conversion-BYOP-vgg16-clustering.zip is provided so users can go right to testing deployment.

Arbitrary Python models, also known as Bring Your Own Predict (BYOP) allow for custom model deployments with supporting scripts and artifacts. These are used with pre-trained models (PyTorch, Tensorflow, etc) along with whatever supporting artifacts they require. Supporting artifacts can include other Python modules, model files, etc. These are zipped with all scripts, artifacts, and a requirements.txt file that indicates what other Python models need to be imported that are outside of the typical Wallaroo platform.

Contrast this with Wallaroo Python models - aka “Python steps”. These are standalone python scripts that use the python libraries natively supported by the Wallaroo platform. These are used for either simple model deployment (such as ARIMA Statsmodels), or data formatting such as the postprocessing steps. A Wallaroo Python model will be composed of one Python script that matches the Wallaroo requirements.

Arbitrary Python File Requirements

Arbitrary Python (BYOP) models are uploaded to Wallaroo via a ZIP file with the following components:

Python scripts aka .py files with classes that extend mac.inference.Inference and mac.inference.creation.InferenceBuilderPython ScriptExtend the classes mac.inference.Inference and mac.inference.creation.InferenceBuilder. These are included with the Wallaroo SDK. Further details are in Arbitrary Python Script Requirements. Note that there is no specified naming requirements for the classes that extend mac.inference.Inference and mac.inference.creation.InferenceBuilder - any qualified class name is sufficient as long as these two classes are extended as defined below.
requirements.txtPython requirements fileThis sets the Python libraries used for the arbitrary python model. These libraries should be targeted for Python 3.8 compliance. These requirements and the versions of libraries should be exactly the same between creating the model and deploying it in Wallaroo. This insures that the script and methods will function exactly the same as during the model creation process.
Other artifactsFilesOther models, files, and other artifacts used in support of this model.

For example, the if the arbitrary python model will be known as vgg_clustering, the contents may be in the following structure, with vgg_clustering as the storage directory:


Note the inclusion of the custom_inference.py file. This file name is not required - any Python script or scripts that extend the classes listed above are sufficient. This Python script could have been named vgg_custom_model.py or any other name as long as it includes the extension of the classes listed above.

The sample arbitrary python model file is created with the command zip -r vgg_clustering.zip vgg_clustering/.

Wallaroo Arbitrary Python uses the Wallaroo SDK mac module, included in the Wallaroo SDK 2023.2.1 and above. See the Wallaroo SDK Install Guides for instructions on installing the Wallaroo SDK.

Arbitrary Python Script Requirements

The entry point of the arbitrary python model is any python script that extends the following classes. These are included with the Wallaroo SDK. The required methods that must be overridden are specified in each section below.

  • mac.inference.Inference interface serves model inferences based on submitted input some input. Its purpose is to serve inferences for any supported arbitrary model framework (e.g. scikit, keras etc.).

        class Inference {
            +model Optional[Any]
            +expected_model_types()* Set
            +predict(input_data: InferenceData)*  InferenceData
            -raise_error_if_model_is_not_assigned() None
            -raise_error_if_model_is_wrong_type() None
  • mac.inference.creation.InferenceBuilder builds a concrete Inference, i.e. instantiates an Inference object, loads the appropriate model and assigns the model to to the Inference object.

        class InferenceBuilder {
            +create(config InferenceConfig) * Inference
            -inference()* Any


mac.inference.Inference Objects

model Optional[Any]An optional list of models that match the supported frameworks from wallaroo.framework.Framework included in the arbitrary python script. Note that this is optional - no models are actually required. A BYOP can refer to a specific model(s) used, be used for data processing and reshaping for later pipeline steps, or other needs.

mac.inference.Inference Methods

expected_model_types (Required)SetReturns a Set of models expected for the inference as defined by the developer. Typically this is a set of one. Wallaroo checks the expected model types to verify that the model submitted through the InferenceBuilder method matches what this Inference class expects.
_predict (input_data: mac.types.InferenceData) (Required)mac.types.InferenceDataThe entry point for the Wallaroo inference with the following input and output parameters that are defined when the model is updated.
  • mac.types.InferenceData: The input InferenceData is a dictionary of numpy arrays derived from the input_schema detailed when the model is uploaded, defined in PyArrow.Schema format.
  • mac.types.InferenceData: The output is a dictionary of numpy arrays as defined by the output parameters defined in PyArrow.Schema format.
The InferenceDataValidationError exception is raised when the input data does not match mac.types.InferenceData.
raise_error_if_model_is_not_assignedN/AError when expected_model_types is not set.
raise_error_if_model_is_wrong_typeN/AError when the model does not match the expected_model_types.


InferenceBuilder builds a concrete Inference, i.e. instantiates an Inference object, loads the appropriate model and assigns the model to the Inference.

    class InferenceBuilder {
        +create(config InferenceConfig) * Inference
        -inference()* Any

Each model that is included requires its own InferenceBuilder. InferenceBuilder loads one model, then submits it to the Inference class when created. The Inference class checks this class against its expected_model_types() Set.

mac.inference.creation.InferenceBuilder Methods

create(config mac.config.inference.CustomInferenceConfig) (Required)The custom Inference instance.Creates an Inference subclass, then assigns a model and attributes. The CustomInferenceConfig is used to retrieve the config.model_path, which is a pathlib.Path object pointing to the folder where the model artifacts are saved. Every artifact loaded must be relative to config.model_path. This is set when the arbitrary python .zip file is uploaded and the environment for running it in Wallaroo is set. For example: loading the artifact vgg_clustering\feature_extractor.h5 would be set with config.model_path \ feature_extractor.h5. The model loaded must match an existing module. For our example, this is from sklearn.cluster import KMeans, and this must match the Inference expected_model_types.
inferencecustom Inference instance.Returns the instantiated custom Inference object created from the create method.

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 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
2023-07-07 16:18:13.974516: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2023-07-07 16:18:13.974543: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.

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 and Helper Functions

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.

We’ll set up some helper functions that will either use existing workspaces and pipelines, or create them if they do not already exist.

import string
import random

# make a random 4 character suffix to prevent overwriting other user's workspaces
suffix= ''.join(random.choice(string.ascii_lowercase) for i in range(4))
workspace_name = f'vgg16-clustering-workspace{suffix}'
pipeline_name = f'vgg16-clustering-pipeline'

model_name = 'vgg16-clustering'
model_file_name = './models/model-auto-conversion-BYOP-vgg16-clustering.zip'
def get_workspace(name):
    workspace = None
    for ws in wl.list_workspaces():
        if ws.name() == name:
            workspace= ws
    if(workspace == None):
        workspace = wl.create_workspace(name)
    return workspace

def get_pipeline(name):
        pipeline = wl.pipelines_by_name(name)[0]
    except EntityNotFoundError:
        pipeline = wl.build_pipeline(name)
    return pipeline

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 = get_workspace(workspace_name)

pipeline = get_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.

model = wl.upload_model(model_name, 
Waiting for model conversion... It may take up to 10.0min.
Model is Pending conversion..Converting..................Ready.
File Namemodel-auto-conversion-BYOP-vgg16-clustering.zip
Image Pathproxy.replicated.com/proxy/wallaroo/ghcr.io/wallaroolabs/mlflow-deploy:v2023.3.0-main-3481
Updated At2023-07-Jul 16:20:20

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.

created2023-06-28 16:37:14.436166+00:00
last_updated2023-07-07 02:09:17.095252+00:00
versions21fb5777-f32d-4b86-99c1-3b099f0f671d, 610afdf4-850d-48f6-aad9-3115f389ee78, 13ed3d22-a82b-4a45-9b1d-5d668e9b2452, 9049c924-146f-4f7a-9e16-0b2565491547
deployment_config = DeploymentConfigBuilder() \
    .cpus(0.25).memory('4Gi') \

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

{‘status’: ‘Running’,
‘details’: [],
’engines’: [{‘ip’: ‘’,
’name’: ’engine-85bd45d44b-dstdp’,
‘status’: ‘Running’,
‘reason’: None,
‘details’: [],
‘pipeline_statuses’: {‘pipelines’: [{‘id’: ‘vgg16-clustering-pipeline’,
‘status’: ‘Running’}]},
‘model_statuses’: {‘models’: [{’name’: ‘vgg16-clustering’,
‘version’: ‘86eaa743-f659-4eac-9544-23893ea0101c’,
‘sha’: ‘9701562daa747b15846ce6e5eb20ba5d8b6ac77c38b62e58298da56252aa493f’,
‘status’: ‘Running’}]}}],
’engine_lbs’: [{‘ip’: ‘’,
’name’: ’engine-lb-584f54c899-8mmpl’,
‘status’: ‘Running’,
‘reason’: None,
‘details’: []}],
‘sidekicks’: [{‘ip’: ‘’,
’name’: ’engine-sidekick-vgg16-clustering-174-79f64f7cb4-25wqf’,
‘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[[[10, 214, 168], [50, 238, 47], [189, 15, 55]...
1[[[10, 214, 168], [50, 238, 47], [189, 15, 55]...
pipeline.infer(dataframe, timeout=10000)
02023-07-07 16:20:48.450[10, 214, 168, 50, 238, 47, 189, 15, 55, 218, ...10
12023-07-07 16:20:48.450[10, 214, 168, 50, 238, 47, 189, 15, 55, 218, ...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
created2023-07-07 16:20:23.354098+00:00
last_updated2023-07-07 16:20:23.354098+00:00