GitHub Repository: ibm/watson-machine-learning-samples
Path: blob/master/cloud/notebooks/python_sdk/deployments/python_function/Use function to recognize hand-written digits.ipynb
⁶⁴⁰⁸ views

Kernel: Python 3 (ipykernel)

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

Create and deploy a function that receives HTML canvas image data from a web app and then processes and sends that data to a model trained to recognize handwritten digits. See: MNIST function deployment tutorial

This notebook runs on Python 3.11.

Learning goals

The learning goals of this notebook are:

AI function definition
Store AI function
Deployment creation

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:

Create a watsonx.ai Runtime Service instance (a free plan is offered and information about how to create the instance can be found here).

Install and import the `ibm-watsonx-ai` and dependecies

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

In [ ]:

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

Connection to watsonx.ai Runtime

Authenticate the watsonx.ai Runtime service on IBM Cloud. You need to provide platform api_key and instance location.

You can use IBM Cloud CLI to retrieve platform API Key and instance location.

API Key can be generated in the following way:

ibmcloud login
ibmcloud iam api-key-create API_KEY_NAME

In result, get the value of api_key from the output.

Location of your watsonx.ai Runtime instance can be retrieved in the following way:

ibmcloud login --apikey API_KEY -a https://cloud.ibm.com
ibmcloud resource service-instance INSTANCE_NAME

In result, get the value of location from the output.

Tip: Your Cloud API key can be generated by going to the Users section of the Cloud console. From that page, click your name, scroll down to the API Keys section, and click Create an IBM Cloud API key. Give your key a name and click Create, then copy the created key and paste it below. You can also get a service specific url by going to the Endpoint URLs section of the watsonx.ai Runtime docs. You can check your instance location in your watsonx.ai Runtime Service instance details.

You can also get service specific apikey by going to the Service IDs section of the Cloud Console. From that page, click Create, then copy the created key and paste it below.

Action: Enter your api_key and location in the following cell.

In [29]:

api_key = 'PASTE YOUR PLATFORM API KEY HERE'
location = 'PASTE YOUR INSTANCE LOCATION HERE'

In [1]:

from ibm_watsonx_ai import Credentials

credentials = Credentials(
    api_key=api_key,
    url='https://' + location + '.ml.cloud.ibm.com'
)

In [2]:

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 Deployment Spaces Dashboard to create one.

Click New Deployment Space
Create an empty space
Select Cloud Object Storage
Select watsonx.ai Runtime instance and press Create
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 [3]:

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 Runtime, you need to set space which you will be using.

In [4]:

client.set.default_space(space_id)

Out[4]:

'SUCCESS'

2. Get an ID for a model deployment

The deployed function created in this notebook is designed to send payload data to a TensorFlow model created in the MNIST tutorials.

In [5]:

import os, wget, json
import numpy as np
import matplotlib.pyplot as plt
import requests

Option 1: Use your own, existing model deployment

If you already deployed a model while working through one of the following MNIST tutorials, you can use that model deployment:

Experiment builder MNIST tutorial

Paste the model deployment ID in the following cell.

See: Looking up an online deployment ID

In [10]:

model_deployment_id = ""

Option 2: Download, store, and deploy a sample model

You can deployed a sample model and get its deployment ID by running the code in the following four cells.

In [6]:

# Download a sample model to the notebook working directory

sample_saved_model_filename = 'mnist-tf-hpo-saved-model.tar.gz'
url = 'https://github.com/IBM/watson-machine-learning-samples/raw/master/cloud/models/tensorflow/mnist/' + sample_saved_model_filename
if not os.path.isfile(sample_saved_model_filename): wget.download(url)

In [7]:

# Look up software specification for the MNIST model

sofware_spec_id = client.software_specifications.get_id_by_name("runtime-24.1-py3.11")

In [8]:

# Store the sample model in your watsonx.ai Runtime repository

metadata = {
            client.repository.ModelMetaNames.NAME: 'Saved MNIST model',
            client.repository.ModelMetaNames.TYPE: 'tensorflow_2.14',
            client.repository.ModelMetaNames.SOFTWARE_SPEC_ID: sofware_spec_id
}
model_details = client.repository.store_model(
    model=sample_saved_model_filename,
    meta_props=metadata
)

In [12]:

# Get published model ID

published_model_id = client.repository.get_model_id(model_details)

In [10]:

# Deploy the stored model
metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "MNIST saved model deployment",
    client.deployments.ConfigurationMetaNames.ONLINE: {}
}

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

Out[10]:

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

Synchronous deployment creation for uid: '3d122ee1-d4b4-4d59-9b6f-ae9c29905e5f' started

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


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


------------------------------------------------------------------------------------------------
Successfully finished deployment creation, deployment_uid='2bee0f99-afd5-489e-9247-3484f2553c67'
------------------------------------------------------------------------------------------------

In [11]:

# Get the ID of the model deployment just created

model_deployment_id = client.deployments.get_id(model_deployment_details)
print(model_deployment_id)

Out[11]:

2bee0f99-afd5-489e-9247-3484f2553c67

3. Get sample canvas data

The deployed function created in this notebook is designed to accept RGBA image data from an HTML canvas object.

Run the following cells to download and view sample canvas data for testing the deployed function.

3.1 Download sample data file

In [13]:

# Download the file containing the sample data

sample_canvas_data_filename = 'mnist-html-canvas-image-data.json'
url = 'https://github.com/IBM/watson-machine-learning-samples/raw/master/cloud/data/mnist/' + sample_canvas_data_filename
if not os.path.isfile(sample_canvas_data_filename): wget.download(url)

In [14]:

# Load the sample data from the file into a variable

with open(sample_canvas_data_filename) as data_file:
    sample_cavas_data = json.load(data_file)

3.2 View sample data

In [15]:

# View the raw contents of the sample data

print("Height (n): " + str(sample_cavas_data["height"]) + " pixels\n")
print("Num image data entries: " + str(len( sample_cavas_data["data"])) + " - (n * n * 4) elements - RGBA values\n")
print(json.dumps(sample_cavas_data, indent=3)[:75] + "...\n" + json.dumps(sample_cavas_data, indent=3)[-50:])

Out[15]:

Height (n): 187 pixels

Num image data entries: 139876 - (n * n * 4) elements - RGBA values

{
   "data": [
      0,
      0,
      0,
      0,
      0,
      0,
      ...
      0,
      0,
      0
   ],
   "height": 187
}

In [16]:

# See what hand-drawn digit the sample data represents

rgba_arr = np.asarray(sample_cavas_data["data"]).astype('uint8')
n = sample_cavas_data["height"]
plt.figure()
plt.imshow( rgba_arr.reshape(n, n, 4))
plt.xticks([])
plt.yticks([])
plt.show()

Out[16]:

4. Create a deployable function

The basics of creating and deploying functions in watsonx.ai Runtime.

4.1 Define the function

Define a Python closure with an inner function named "score".
Use default parameters to save your watsonx.ai Runtime credentials and the model deployment ID with the deployed function.
Process the canvas data (reshape and normalize) and then send the processed data to the model deployment.
Process the results from the model deployment so the deployed function returns simpler results.
Implement error handling so the function will behave gracefully if there is an error.

In [17]:

ai_parms = {"credentials": credentials.__dict__, "space_id": space_id, "model_deployment_id": model_deployment_id}

def my_deployable_function( parms=ai_parms ):        
    def getRGBAArr(canvas_data):
        import numpy as np
        dimension = canvas_data["height"]
        rgba_data = canvas_data["data"]
        rgba_arr  = np.asarray(rgba_data).astype('uint8')
        return rgba_arr.reshape(dimension, dimension, 4)
        
    def getNormAlphaList(img):
        import numpy as np
        alpha_arr       = np.array(img.split()[-1])
        norm_alpha_arr  = alpha_arr / 255
        norm_alpha_list = norm_alpha_arr.reshape(1, 784).tolist()
        return norm_alpha_list
        
    def score(function_payload):
            
        try:
            
            from PIL import Image
            canvas_data   = function_payload["input_data"][0]["values"][0]           # Read the payload received by the function
            rgba_arr      = getRGBAArr(canvas_data)               # Create an array object with the required shape
            img           = Image.fromarray(rgba_arr, 'RGBA')     # Create an image object that can be resized
            sm_img        = img.resize((28, 28), Image.LANCZOS) # Resize the image to 28 x 28 pixels
            alpha_list    = getNormAlphaList(sm_img)              # Create a 1 x 784 array of values between 0 and 1
            model_payload = {"input_data": [{"values" : alpha_list}]}               # Create a payload to be sent to the model
                    
            #print( "Payload for model:" ) # For debugging purposes
            #print( model_payload )        # For debugging purposes
                    
            from ibm_watsonx_ai import APIClient
            client       = APIClient(parms["credentials"])
            client.set.default_space(parms["space_id"])
            model_result = client.deployments.score(parms["model_deployment_id"], model_payload)
            digit_class  = model_result["predictions"][0]["values"][0]
                    
            return model_result
        
        except Exception as e:
            
            return {'predictions': [{'values': [repr(e)]}]}
            #return {"error" : repr(e)}


    return score

4.2 Test locally

You can test your function in the notebook before deploying the function.

To see debugging info:

Uncomment the print statements inside the score function
Rerun the cell defining the function
When you rerun the this cell, you will see the debugging info

In [18]:

# Pass the sample canvas data to the function as a test

func_result = my_deployable_function()({"input_data": [{"values": [sample_cavas_data]}]})
print(func_result)

Out[18]:

{'predictions': [{'id': 'classes', 'values': [4]}]}

5. Store and deploy the function

Before you can deploy the function, you must store the function in your watsonx.ai Runtime repository.

In [19]:

# Look up software specification for the deployable function

sofware_spec_id = client.software_specifications.get_id_by_name("runtime-24.1-py3.11")

In [20]:

# Store the deployable function in your watsonx.ai Runtime repository

meta_data = {
    client.repository.FunctionMetaNames.NAME: 'MNIST deployable function',
    client.repository.FunctionMetaNames.SOFTWARE_SPEC_ID: sofware_spec_id
}

function_details = client.repository.store_function(meta_props=meta_data, function=my_deployable_function)

In [21]:

# Get published function ID

function_id = client.repository.get_function_id(function_details)

In [22]:

# Deploy the stored function

metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "MNIST function deployment",
    client.deployments.ConfigurationMetaNames.ONLINE: {}
}

function_deployment_details = client.deployments.create(function_id, meta_props=metadata)

Out[22]:

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

Synchronous deployment creation for uid: 'f445406f-b081-4c22-9ccd-f2bd9f93dfb5' started

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


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


------------------------------------------------------------------------------------------------
Successfully finished deployment creation, deployment_uid='d0807ae6-b8dc-4859-858d-554b273b3301'
------------------------------------------------------------------------------------------------

6. Test the deployed function

You can use the watsonx.ai Python client or REST API to send data to your function deployment for processing in exactly the same way you send data to model deployments for processing.

In [ ]:

# Get the endpoint URL of the function deployment just created

function_deployment_id = client.deployments.get_id(function_deployment_details)
function_deployment_endpoint_url = client.deployments.get_scoring_href(function_deployment_details)
print(function_deployment_id)
print(function_deployment_endpoint_url)

In [24]:

payload = {"input_data": [{"values": [sample_cavas_data]}]}

6.1 watsonx.ai Python client

In [25]:

result = client.deployments.score(function_deployment_id, payload)
if "error" in result:
    print(result["error"])
else:
    print(result)

Out[25]:

{'predictions': [{'id': 'classes', 'values': [4]}]}

6.2 watsonx.ai REST API example

In [26]:

# Get an IAM token from IBM Cloud
url     = "https://iam.bluemix.net/oidc/token"
headers = {"Content-Type": "application/x-www-form-urlencoded"}
data    = "apikey=" + credentials["apikey"] + "&grant_type=urn:ibm:params:oauth:grant-type:apikey"
IBM_cloud_iam_id = "bx"
IBM_cloud_iam_pwd = "bx"
response  = requests.post(url, headers=headers, data=data, auth=(IBM_cloud_iam_id, IBM_cloud_iam_pwd))

if 200 != response.status_code:
    print(response.status_code)
    print(response.reason)
else:
    iam_token = response.json()["access_token"]
    
    # Send data to deployment for processing
    headers = {"Content-Type"   : "application/json",
               "Authorization"  : "Bearer " + iam_token}
    params = {"version": "2020-08-01"}
    response = requests.post(function_deployment_endpoint_url, json=payload, params=params, headers=headers)
    print(response.text)

Out[26]:

{"predictions":[{"id":"classes","values":[4]}]}

7. 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.

8. Summary and next steps

In this notebook, you created a Python function that receives HTML canvas image data and then processes and sends that data to a model trained to recognize handwritten digits.

Authors

Sarah Packowski is a member of the IBM Watson Studio Content Design team in Canada.

Mateusz Szewczyk, Software Engineer at watsonx.ai

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

Learning goals

Contents

1. Set up the environment

Install and import the `ibm-watsonx-ai` and dependecies

Connection to watsonx.ai Runtime

Working with spaces

2. Get an ID for a model deployment

Option 1: Use your own, existing model deployment

Option 2: Download, store, and deploy a sample model

3. Get sample canvas data

3.1 Download sample data file

3.2 View sample data

4. Create a deployable function

4.1 Define the function

4.2 Test locally

5. Store and deploy the function

6. Test the deployed function

6.1 watsonx.ai Python client

6.2 watsonx.ai REST API example

7. Clean up

8. Summary and next steps

Authors

Product

Resources

Company

Use Python function to recognize hand-written digits with ibm-watsonx-ai

Learning goals

Contents

1. Set up the environment

Install and import the ibm-watsonx-ai and dependecies

Connection to watsonx.ai Runtime

Working with spaces

2. Get an ID for a model deployment

Option 1: Use your own, existing model deployment

Option 2: Download, store, and deploy a sample model

3. Get sample canvas data

3.1 Download sample data file

3.2 View sample data

4. Create a deployable function

4.1 Define the function

4.2 Test locally

5. Store and deploy the function

6. Test the deployed function

6.1 watsonx.ai Python client

6.2 watsonx.ai REST API example

7. Clean up

8. Summary and next steps

Authors

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

Install and import the `ibm-watsonx-ai` and dependecies