Use ONNX model converted from TensorFlow to recognize hand-written digits with ibm-watsonx-ai
¶
This notebook facilitates ONNX, TensorFlow (Keras), and Watson Machine Learning service. It contains steps and code to work with ibm-watsonx-ai library available in PyPI repository in order to convert the TensorFlow model to ONNX format. 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 3.11.
Learning goals¶
The learning goals of this notebook are:
- Download an externally trained TensorFlow model with dataset.
- Convert TensorFlow model to ONNX format
- Persist converted model in Watson Machine Learning repository.
- Deploy model for online scoring using client library.
- Score sample records using client library.
Contents¶
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 Watson Machine Learning (WML) Service instance (a free plan is offered and information about how to create the instance can be found here).
!pip install wget | tail -n 1
!pip install matplotlib | tail -n 1
!pip install -U ibm-watsonx-ai | tail -n 1
!pip install tensorflow==2.14 | tail -n 1
!pip install tf2onnx==1.16 | tail -n 1
!pip install onnxruntime==1.16.3 | tail -n 1
import json
import logging
import tf2onnx
from pathlib import Path
import matplotlib.pyplot as plt
import numpy as np
import onnx
import onnxruntime as ort
import wget
from ibm_watsonx_ai import Credentials, APIClient
from keras.models import load_model
Connection to WML¶
Authenticate to the Watson Machine Learning 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 WML instance can be retrieved in the following way:
ibmcloud login --apikey API_KEY -a https://cloud.ibm.com
ibmcloud resource service-instance WML_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 Watson Machine Learning docs. You can check your instance location in your Watson Machine Learning (WML) 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.
api_key = 'PASTE YOUR PLATFORM API KEY HERE'
location = 'PASTE YOUR INSTANCE LOCATION HERE'
credentials = Credentials(
api_key=api_key,
url=f'https://{location}.ml.cloud.ibm.com'
)
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 Watson Machine Learning 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
space_id = 'PASTE YOUR SPACE ID HERE'
You can use list
method to print all existing spaces.
client.spaces.list(limit=10)
To be able to interact with all resources available in Watson Machine Learning, you need to set space which you will be using.
client.set.default_space(space_id)
'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. You can choose to download either a TensorFlow or a Keras model.
2.1. Download dataset¶
data_dir = Path('MNIST_DATA')
if not data_dir.is_dir():
data_dir.mkdir()
data_path = data_dir / 'mnist.npz'
if not data_path.is_file():
wget.download('https://s3.amazonaws.com/img-datasets/mnist.npz', out=str(data_dir))
dataset = np.load(data_path)
x_test = dataset['x_test']
2.2. Download TensorFlow model¶
tf_model_name = 'mnist-tf-hpo-saved-model'
model_tar_name = f'{tf_model_name}.tar.gz'
model_path = data_dir / model_tar_name
if not model_path.is_file():
wget.download(f"https://github.com/IBM/watson-machine-learning-samples/raw/master/cloud/models/tensorflow/mnist/{model_tar_name}", out=str(data_dir))
2.3. (OPTIONAL) Download TensorFLow Keras model¶
To download the TensorFLow Keras model, change the Markdown
cell below to a Code
cell and remove the triple backticks (```
).
tf_model_name = 'mnist_cnn.h5'
model_tar_name = f'mnist_keras.h5.tgz'
model_path = data_dir / model_tar_name
if not model_path.is_file():
wget.download(f"https://github.com/IBM/watson-machine-learning-samples/raw/master/cloud/models/keras/{model_tar_name}", out=str(data_dir))
onnx_model_name = "mnist_cnn.onnx"
3.1. Converting TensorFlow SavedModel¶
!mkdir -p {tf_model_name}
!tar xzf MNIST_DATA/{model_tar_name} -C {tf_model_name}
Note: If you are working with TensorFlow Lite models, make sure to use the --tflite
flag instead of --saved-model
.
!python -m tf2onnx.convert --saved-model {tf_model_name} --output {onnx_model_name}
onnx_model = onnx.load(onnx_model_name)
3.2. (OPTIONAL) Converting TensorFLow Keras model¶
To convert the TensorFLow Keras model to ONNX format, change the Markdown
cells below to a Code
cells and remove the triple backticks (```
).
!tar xzf MNIST_DATA/{model_tar_name}
logging.getLogger().setLevel(logging.ERROR)
model = load_model(tf_model_name)
onnx_model, _ = tf2onnx.convert.from_keras(model)
onnx.save(onnx_model, onnx_model_name)
3.3. Validating the ONNX Model¶
After exporting the model, you should verify its integrity and ensure that it functions as expected. We will use onnxruntime
to load the model and perform inference on the random dataset. Additionally, we’ll use onnx
's checker
module to validate the exported ONNX model.
onnx.checker.check_model(onnx_model)
session = ort.InferenceSession(onnx_model_name)
x_test = np.array(x_test, dtype=np.float32).reshape(-1, 784) # flattened image 28*28=784
input_data = {session.get_inputs()[0].name: x_test}
output = session.run([], input_data)
4. Persist converted ONNX model¶
In this section, you will learn how to store your converted ONNX model in Watson Machine Learning repository using the IBM Watson Machine Learning SDK.
4.1. Publish model in Watson Machine Learning repository¶
Define model name, type and software spec.
sofware_spec_id = client.software_specifications.get_id_by_name("onnxruntime_opset_19")
onnx_model_zip = "mnist_cnn.zip"
!zip {onnx_model_zip} {onnx_model_name}
updating: mnist_cnn.onnx (deflated 7%)
metadata = {
client.repository.ModelMetaNames.NAME: 'TensorFLow to ONNX converted model',
client.repository.ModelMetaNames.TYPE: 'onnxruntime_1.16',
client.repository.ModelMetaNames.SOFTWARE_SPEC_ID: sofware_spec_id
}
published_model = client.repository.store_model(
model=onnx_model_zip,
meta_props=metadata
)
4.2. Get model details¶
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))
{ "entity": { "hybrid_pipeline_software_specs": [], "software_spec": { "id": "368d2795-aaa7-59a0-834c-248c64a5a99e", "name": "onnxruntime_opset_19" }, "type": "onnxruntime_1.16" }, "metadata": { "created_at": "2024-11-26T17:55:47.029Z", "id": "29209363-d885-472a-aa11-e69f1db0c2ec", "modified_at": "2024-11-26T17:55:55.987Z", "name": "TensorFLow to ONNX converted model", "owner": "IBMid-6980008OAA", "resource_key": "736795e1-0ae1-4b9c-9f74-48ed534fbb84", "space_id": "1cfa7b13-df10-4ab3-8df6-a10e8ac43780" }, "system": { "warnings": [] } }
5. Deploy and score ONNX model¶
In this section you'll learn how to create an online scoring service and predict on unseen data.
5.1. Create online deployment for published model¶
metadata = {
client.deployments.ConfigurationMetaNames.NAME: "Deployment of TensorFLow to ONNX converted model",
client.deployments.ConfigurationMetaNames.ONLINE: {}
}
created_deployment = client.deployments.create(published_model_id, meta_props=metadata)
###################################################################################### Synchronous deployment creation for id: '29209363-d885-472a-aa11-e69f1db0c2ec' 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_id='ed314c63-4bac-4501-8beb-1067c46cfe33' -----------------------------------------------------------------------------------------------
deployment_id = client.deployments.get_id(created_deployment)
Now you can print an online scoring endpoint.
client.deployments.get_scoring_href(created_deployment)
You can also list existing deployments.
client.deployments.list()
5.2. Get deployment details¶
client.deployments.get_details(deployment_id)
5.3. 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.
%matplotlib inline
for i, image in enumerate([x_test[0], x_test[1]]):
plt.subplot(2, 2, i + 1)
plt.axis('off')
plt.imshow(image.reshape((28, 28)), cmap=plt.cm.gray_r, interpolation='nearest')
Prepare scoring payload with records to score.
score_0 = x_test[0].tolist()
score_1 = x_test[1].tolist()
scoring_payload = {"input_data": [{"values": [score_0, score_1]}]}
Use client.deployments.score()
method to run scoring.
predictions = client.deployments.score(deployment_id, scoring_payload)
Let's print the result of predictions.
print(json.dumps(predictions, indent=2))
{ "predictions": [ { "id": "classes", "values": [ 7, 2 ] } ] }
As you can see, predicted values are the same one as displayed above from test dataset.
6. Clean up¶
If you want to clean up after the notebook execution, i.e. remove any created assets like: please follow up this sample notebook.
- experiments
- trainings
- pipelines
- model definitions
- models
- functions
- deployments
7. Summary and next steps¶
You successfully completed this notebook! You learned how to use ONNX, TensorFlow machine learning library as well as Watson Machine Learning for model creation and deployment. Check out our Online Documentation for more samples, tutorials, documentation, how-tos, and blog posts.
Authors¶
Michał Koruszowic, Software Engineer
Copyright © 2024 IBM. This notebook and its source code are released under the terms of the MIT License.