Model serving (TF Serving) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a TensorFlow SavedModel for serving.

TensorFlow

import tensorflow as tf
model = tf.saved_model.load([1])

Drag options to blanks, or click blank then click option'

Atf_model

Bmodel_path

C'model_path'

Dload_model

Attempts:

3 left

💡 Hint

Common Mistakes

Forgetting to put quotes around the model path.

Using a variable name without defining it.

The model path must be a string specifying the directory where the SavedModel is stored.

2fill in blank

medium

Complete the code to create a TensorFlow Serving signature for prediction.

TensorFlow

infer = model.signatures[[1]]

Drag options to blanks, or click blank then click option'

Aserving_default

B'serving_default'

C'predict'

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using the signature name without quotes.

Using an incorrect signature key.

The signature key must be a string matching the saved signature name, usually 'serving_default'.

3fill in blank

hard

Fix the error in the code to prepare input tensor for serving.

TensorFlow

import tensorflow as tf
input_tensor = tf.constant([1])

Drag options to blanks, or click blank then click option'

A[[1.0, 2.0, 3.0]]

Barray([1.0, 2.0, 3.0])

Ctf.Tensor([1.0, 2.0, 3.0])

D1.0, 2.0, 3.0

Attempts:

3 left

💡 Hint

Common Mistakes

Passing multiple arguments instead of a list.

Using non-TensorFlow array types.

tf.constant expects a list or nested list to create a tensor; a nested list represents batch input.

4fill in blank

hard

Fill both blanks to run inference and get the prediction output.

TensorFlow

output = infer([1])
prediction = output[[2]]

Drag options to blanks, or click blank then click option'

A'input_1'

Binput_tensor

C'output_1'

Doutput_tensor

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the input key string instead of the tensor variable.

Using variable names instead of output key strings.

The input tensor variable is passed to the signature, and the output is accessed by the output key string.

5fill in blank

hard

Fill all three blanks to define a simple TF Serving REST API using Flask.

TensorFlow

from flask import Flask, request, jsonify
import tensorflow as tf

app = Flask(__name__)
model = tf.saved_model.load([1])
infer = model.signatures[[2]]

@app.route('/predict', methods=['POST'])
def predict():
    data = request.get_json()
    input_tensor = tf.constant(data[[3]])
    output = infer(input_tensor)
    return jsonify({'prediction': output['output_1'].numpy().tolist()})

Drag options to blanks, or click blank then click option'

A'model_dir'

B'serving_default'

C'input_data'

D'input_tensor'

Attempts:

3 left

💡 Hint

Common Mistakes

Using variable names instead of strings for model path or signature.

Mismatching JSON input key.

The model directory is a string path, the signature key is 'serving_default', and the JSON input key is 'input_data'.

Practice

1. What is the main purpose of TensorFlow Serving in machine learning?

easy

A. To clean and preprocess data before training

B. To train new machine learning models

C. To visualize model training progress

D. To deploy trained models for real-time predictions

Solution

1. Step 1: Understand TensorFlow Serving's role

   TensorFlow Serving is designed to deploy models so they can be used to make predictions quickly.

2. Step 2: Differentiate from training and preprocessing

   Training and preprocessing happen before serving; TensorFlow Serving focuses on using the trained model.

3. Final Answer:

   To deploy trained models for real-time predictions -> Option D

4. Quick Check:

   Serving = Deploy models for predictions [OK]

Hint: Serving means deploying models to answer queries fast [OK]

Common Mistakes:

• Confusing serving with training
• Thinking it preprocesses data
• Assuming it visualizes training

2. Which command correctly starts TensorFlow Serving to serve a model saved at /models/my_model?

easy

A. tensorflow_model_server --model_base_path=/models/my_model --rest_api_port=8501

B. tensorflow_serve --model_path=/models/my_model --port=8501

C. serve_tf_model --model_dir=/models/my_model --grpc_port=8501

D. start_tf_server --model=/models/my_model --api_port=8501

Solution

1. Step 1: Identify the official TensorFlow Serving command

   The official command is tensorflow_model_server with flags like --model_base_path and --rest_api_port.

2. Step 2: Match the correct flags and path

   tensorflow_model_server --model_base_path=/models/my_model --rest_api_port=8501 uses correct command and flags pointing to /models/my_model and port 8501.

3. Final Answer:

   tensorflow_model_server --model_base_path=/models/my_model --rest_api_port=8501 -> Option A

4. Quick Check:

   Correct command and flags = tensorflow_model_server --model_base_path=/models/my_model --rest_api_port=8501 [OK]

Hint: Look for 'tensorflow_model_server' and '--model_base_path' flags [OK]

Common Mistakes:

• Using wrong command name
• Incorrect flag names
• Wrong model path flag

3. Given this Python code snippet sending data to TensorFlow Serving REST API, what is the expected output if the model predicts class 1 with 0.85 confidence?

import requests
import json

url = 'http://localhost:8501/v1/models/my_model:predict'
data = {"instances": [[5.1, 3.5, 1.4, 0.2]]}
response = requests.post(url, json=data)
print(response.json())

medium

A. {"predictions": [[1, 0.85]]}

B. {"predictions": [[1]]}

C. {"predictions": [[0.85, 1]]}

D. {"error": "Model not found"}

Solution

1. Step 1: Understand the REST API response format

   TensorFlow Serving returns predictions as a list of outputs matching the model's output shape. For classification, usually a class label or probabilities.

2. Step 2: Match the expected output for class prediction

   If the model predicts class 1 with confidence 0.85, the output is typically the class label only, e.g., [1].

3. Final Answer:

   {"predictions": [[1]]} -> Option B

4. Quick Check:

   Prediction output = class label list [OK]

Hint: REST API returns predictions list matching model output shape [OK]

Common Mistakes:

• Confusing confidence with class label
• Expecting confidence and label together
• Ignoring model output format

4. You started TensorFlow Serving with this command:
tensorflow_model_server --model_base_path=/models/my_model --rest_api_port=8501
But when you send a request, you get a 404 error. What is the most likely cause?

medium

A. The model folder path is incorrect or missing the version subfolder

B. The REST API port 8501 is blocked by firewall

C. The client request JSON format is wrong

D. TensorFlow Serving does not support REST API

Solution

1. Step 1: Check model folder structure requirement

   TensorFlow Serving expects the model folder to contain version subfolders like 1/, 2/ with saved model files inside.

2. Step 2: Understand 404 error meaning

   A 404 error means the server cannot find the requested model, often due to missing or wrong model path or version folder.

3. Final Answer:

   The model folder path is incorrect or missing the version subfolder -> Option A

4. Quick Check:

   404 error = model path/version issue [OK]

Hint: Model folder must have version subfolders like '1/' [OK]

Common Mistakes:

• Ignoring model folder versioning
• Assuming REST API unsupported
• Blaming firewall without checking model path

5. You want to serve two different versions of a model simultaneously using TensorFlow Serving. Which setup allows clients to request a specific version?

hard

A. Rename model folders to different names and serve them under separate model names

B. Run two separate TensorFlow Serving servers on different ports, each serving one version

C. Place version folders (e.g., 1/, 2/) inside the model base path and use the version parameter in the request URL

D. TensorFlow Serving does not support serving multiple versions simultaneously

Solution

1. Step 1: Understand versioning in TensorFlow Serving

   TensorFlow Serving supports multiple versions by placing them as subfolders inside the model base path, e.g., 1/, 2/.

2. Step 2: How clients request specific versions

   Clients can specify the version in the request URL to get predictions from a particular version.

3. Final Answer:

   Place version folders (e.g., 1/, 2/) inside the model base path and use the version parameter in the request URL -> Option C

4. Quick Check:

   Version folders + version param = multiple versions [OK]

Hint: Use version folders and version param in request URL [OK]

Common Mistakes:

• Thinking separate servers are needed
• Renaming folders instead of versioning
• Believing multiple versions unsupported