GitHub Repository: ibm/watson-machine-learning-samples
Path: blob/master/cpd5.2/notebooks/python_sdk/deployments/tensorflow/Use Tensorflow to recognize hand-written digits.ipynb
⁶⁴¹² views

Kernel: watsonx-ai-samples-py-312

Use Tensorflow to recognize hand-written digits with `ibm-watsonx-ai`

This notebook facilitates Tensorflow and watsonx.ai service. It contains steps and code to work with ibm-watsonx-ai library available in PyPI repository. It also introduces commands for getting model and training data, persisting model, deploying model and scoring it.

Some familiarity with Python is helpful. This notebook uses Python 3.12.

Learning goals

The learning goals of this notebook are:

Download an externally trained Tensorflow model with dataset.
Persist an external model in watsonx.ai repository.
Deploy model for online scoring using client library.
Score sample records using client library.

This notebook contains the following parts:

1. Set up the environment

Before you use the sample code in this notebook, you must perform the following setup tasks:

Contact with your Cloud Pak for Data administrator and ask them for your account credentials

Install dependencies

Note: ibm-watsonx-ai documentation can be found here.

In [1]:

%pip install -U wget | tail -n 1
%pip install -U matplotlib | tail -n 1
%pip install -U ibm-watsonx-ai | tail -n 1

Out[1]:

Successfully installed wget-3.2
Successfully installed contourpy-1.3.2 cycler-0.12.1 fonttools-4.58.4 kiwisolver-1.4.8 matplotlib-3.10.3 numpy-2.3.0 pillow-11.2.1 pyparsing-3.2.3
Successfully installed anyio-4.9.0 certifi-2025.6.15 charset_normalizer-3.4.2 h11-0.16.0 httpcore-1.0.9 httpx-0.28.1 ibm-cos-sdk-2.14.2 ibm-cos-sdk-core-2.14.2 ibm-cos-sdk-s3transfer-2.14.2 ibm-watsonx-ai-1.3.26 idna-3.10 jmespath-1.0.1 lomond-0.3.3 pandas-2.2.3 pytz-2025.2 requests-2.32.4 sniffio-1.3.1 tabulate-0.9.0 typing_extensions-4.14.0 tzdata-2025.2 urllib3-2.5.0

Define credentials

Authenticate the watsonx.ai Runtime service on IBM Cloud Pak for Data. You need to provide the admin's username and the platform url.

In [2]:

username = "PASTE YOUR USERNAME HERE"
url = "PASTE THE PLATFORM URL HERE"

Use the admin's api_key to authenticate watsonx.ai Runtime services:

In [ ]:

import getpass
from ibm_watsonx_ai import Credentials

credentials = Credentials(
    username=username,
    api_key=getpass.getpass("Enter your watsonx.ai API key and hit enter: "),
    url=url,
    instance_id="openshift",
    version="5.2",
)

Alternatively you can use the admin's password:

In [3]:

import getpass
from ibm_watsonx_ai import Credentials

if "credentials" not in locals() or not credentials.api_key:
    credentials = Credentials(
        username=username,
        password=getpass.getpass("Enter your watsonx.ai password and hit enter: "),
        url=url,
        instance_id="openshift",
        version="5.2",
    )

Create `APIClient` instance

In [4]:

from ibm_watsonx_ai import APIClient

client = APIClient(credentials)

Working with spaces

First of all, you need to create a space that will be used for your work. If you do not have space already created, you can use {PLATFORM_URL}/ml-runtime/spaces?context=icp4data to create one.

Click New Deployment Space
Create an empty space
Go to space Settings tab
Copy space_id and paste it below

Tip: You can also use SDK to prepare the space for your work. More information can be found here.

Action: Assign space ID below

In [5]:

space_id = "PASTE YOUR SPACE ID HERE"

You can use list method to print all existing spaces.

In [ ]:

client.spaces.list(limit=10)

To be able to interact with all resources available in watsonx.ai, you need to set space which you will be using.

In [6]:

client.set.default_space(space_id)

Out[6]:

'SUCCESS'

2. Download externally created Tensorflow model and data

In this section, you will download externally created Tensorflow models and data used for training it.

In [7]:

import os
import wget


model_file = "mnist-tf-model.tar.gz"
if not os.path.isfile(model_file):
    wget.download(
        f"https://github.com/IBM/watsonx-ai-samples/raw/master/cpd5.2/models/tensorflow/mnist/{model_file}"
    )

In [8]:

data_dir = "MNIST_DATA"
if not os.path.isdir(data_dir):
    os.mkdir(data_dir)

filename = os.path.join(data_dir, "mnist.npz")
if not os.path.isfile(filename):
    wget.download("https://s3.amazonaws.com/img-datasets/mnist.npz", out=data_dir)

In [9]:

import numpy as np

dataset = np.load(filename)
x_test = dataset["x_test"]

3. Persist externally created Tensorflow model

In this section, you will learn how to store your model in watsonx.ai repository by using the IBM watsonx.ai SDK.

3.1: Publish model

Publish model in watsonx.ai repository on Cloud.

Define model name, autor name and email.

In [10]:

software_spec_id = client.software_specifications.get_id_by_name("runtime-25.1-py3.12")

In [11]:

metadata = {
    client.repository.ModelMetaNames.NAME: "External Tensorflow model",
    client.repository.ModelMetaNames.TYPE: "tensorflow_2.18",
    client.repository.ModelMetaNames.SOFTWARE_SPEC_ID: software_spec_id,
}

published_model = client.repository.store_model(model=model_file, meta_props=metadata)

3.2: Get model details

In [12]:

import json

published_model_id = client.repository.get_model_id(published_model)
model_details = client.repository.get_details(published_model_id)
print(json.dumps(model_details, indent=2))

Out[12]:

{
  "metadata": {
    "name": "External Tensorflow model",
    "space_id": "8a13841b-df99-4b4d-bf2a-161ad2e33980",
    "resource_key": "7e88fb87-66ad-4da5-a2a0-37e61e5b10a7",
    "id": "41ed6797-5079-4a43-9f5d-e5e5b1317e92",
    "created_at": "2025-06-20T09:49:01Z",
    "rov": {
      "member_roles": {
        "1000331001": {
          "user_iam_id": "1000331001",
          "roles": [
            "OWNER"
          ]
        }
      }
    },
    "owner": "1000331001"
  },
  "entity": {
    "software_spec": {
      "id": "f47ae1c3-198e-5718-b59d-2ea471561e9e"
    },
    "type": "tensorflow_2.18"
  }
}

3.3 Get all models

In [13]:

models_details = client.repository.list_models()

4. Deploy and score

In this section you will learn how to create online scoring and to score a new data record by using the IBM watsonx.ai SDK.

4.1: Create model deployment

Create online deployment for published model

In [14]:

metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "Deployment of external Tensorflow model",
    client.deployments.ConfigurationMetaNames.ONLINE: {},
}

created_deployment = client.deployments.create(published_model_id, meta_props=metadata)

Out[14]:

######################################################################################

Synchronous deployment creation for id: '41ed6797-5079-4a43-9f5d-e5e5b1317e92' started

######################################################################################


initializing
Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.
......
ready


-----------------------------------------------------------------------------------------------
Successfully finished deployment creation, deployment_id='74f8eb5b-9eac-4dd3-8964-0312bdb13a96'
-----------------------------------------------------------------------------------------------

Note: Here we use deployment URL saved in published_model object. In next section, we show how to retrieve deployment URL from watsonx.ai instance.

In [15]:

deployment_id = client.deployments.get_id(created_deployment)

Now you can print an online scoring endpoint.

In [ ]:

scoring_endpoint = client.deployments.get_scoring_href(created_deployment)
print(scoring_endpoint)

You can also list existing deployments.

In [17]:

client.deployments.list()

Out[17]:

4.2: Get deployment details

In [ ]:

client.deployments.get_details(deployment_id)

4.3: Score

You can use below method to do test scoring request against deployed model.

Let's first visualize two samples from dataset, we'll use for scoring.

In [19]:

%matplotlib inline
import matplotlib.pyplot as plt

In [20]:

for i, image in enumerate(x_test[:2]):
    plt.subplot(2, 2, i + 1)
    plt.axis("off")
    plt.imshow(image, cmap=plt.cm.gray_r, interpolation="nearest")

Out[20]:

Prepare scoring payload with records to score.

In [21]:

score_0 = x_test[0].reshape(28, 28, 1)
score_1 = x_test[1].reshape(28, 28, 1)

In [22]:

scoring_payload = {"input_data": [{"values": [score_0, score_1]}]}

Use client.deployments.score() method to run scoring.

In [23]:

predictions = client.deployments.score(deployment_id, scoring_payload)

Let's print the result of predictions.

In [24]:

import json

print(json.dumps(predictions, indent=2))

Out[24]:

{
  "predictions": [
    {
      "id": "output_0",
      "values": [
        [
          1.1042998737664789e-09,
          1.1556646306587481e-08,
          1.692715656531618e-08,
          1.9323502867263365e-11,
          1.1548956457829718e-08,
          7.011491539275772e-13,
          1.2946564709181985e-07,
          0.9999977350234985,
          1.3095871054247255e-06,
          8.285622925541247e-07
        ],
        [
          0.003000207943841815,
          0.023734718561172485,
          0.698652446269989,
          0.008241103030741215,
          0.013524111360311508,
          0.012331295758485794,
          0.20740151405334473,
          0.001026318990625441,
          0.029136182740330696,
          0.002952153328806162
        ]
      ]
    }
  ]
}

In [25]:

for i, prediction in enumerate(predictions["predictions"][0]["values"]):
    plt.bar(range(10), prediction)
    plt.title("Digit probability")
    plt.xlabel("Digit")
    plt.ylabel("Probability")
    plt.xticks(range(10))
    plt.yscale("log")
    plt.show()

Out[25]:

As you can see, predicted values are the same one as displayed above from test dataset.

5. Clean up

If you want to clean up all created assets:

experiments
trainings
pipelines
model definitions
models
functions
deployments

please follow up this sample notebook.

6. Summary and next steps

You successfully completed this notebook! You learned how to use Tensorflow as well as watsonx.ai for model creation and deployment.

Check out our Online Documentation for more samples, tutorials, documentation, how-tos, and blog posts.

Authors

Daniel Ryszka, Software Engineer

Rafał Chrzanowski, Software Engineer Intern at watsonx.ai.

Use Tensorflow to recognize hand-written digits with `ibm-watsonx-ai`

Learning goals

Contents

1. Set up the environment

Install dependencies

Define credentials

Create `APIClient` instance

Working with spaces

2. Download externally created Tensorflow model and data

3. Persist externally created Tensorflow model

3.1: Publish model

Publish model in watsonx.ai repository on Cloud.

3.2: Get model details

3.3 Get all models

4. Deploy and score

4.1: Create model deployment

Create online deployment for published model

4.2: Get deployment details

4.3: Score

5. Clean up

6. Summary and next steps

Authors

Product

Resources

Company

Use Tensorflow to recognize hand-written digits with ibm-watsonx-ai

Learning goals

Contents

1. Set up the environment

Install dependencies

Define credentials

Create APIClient instance

Working with spaces

2. Download externally created Tensorflow model and data

3. Persist externally created Tensorflow model

3.1: Publish model

Publish model in watsonx.ai repository on Cloud.

3.2: Get model details

3.3 Get all models

4. Deploy and score

4.1: Create model deployment

Create online deployment for published model

4.2: Get deployment details

4.3: Score

5. Clean up

6. Summary and next steps

Authors

Use Tensorflow to recognize hand-written digits with `ibm-watsonx-ai`

Create `APIClient` instance