Model serving (TF Serving) in TensorFlow - ML Experiment: Train & Evaluate

Experiment - Model serving (TF Serving)

Problem:You have trained a TensorFlow model for image classification. Now you want to serve this model so that other applications can send images and get predictions in real-time.

Current Metrics:Model accuracy on test data: 92%. Model is saved as a .h5 file but not yet served.

Issue:The model is not accessible for real-time predictions. You need to deploy it using TensorFlow Serving to handle requests efficiently.

Your Task

Deploy the trained TensorFlow model using TensorFlow Serving and test it by sending sample image data to get prediction results.

Use TensorFlow Serving Docker container for deployment.

Serve the model on localhost port 8501.

Use REST API to send prediction requests.

Do not retrain or change the model architecture.

Hint 1

Hint 2

Hint 3

Hint 4

Solution

TensorFlow

import tensorflow as tf
import numpy as np
import requests
import json
import base64

# Step 1: Export the model in SavedModel format
model = tf.keras.models.load_model('my_model.h5')
saved_model_path = 'exported_model/1'
tf.saved_model.save(model, saved_model_path)

# Step 2: Run TensorFlow Serving Docker container (run this in terminal, not Python)
# docker run -p 8501:8501 --name tf_serving_model \
# -v "$(pwd)/exported_model:/models/my_model" \
# -e MODEL_NAME=my_model -t tensorflow/serving

# Step 3: Prepare a sample input image (dummy data here for example)
input_data = np.random.rand(1, 28, 28, 1).astype(np.float32)  # Example for MNIST-like model

# Convert input to list for JSON serialization
input_list = input_data.tolist()

# Step 4: Create JSON request
json_request = json.dumps({"signature_name": "serving_default", "instances": input_list})

# Step 5: Send POST request to TF Serving REST API
url = 'http://localhost:8501/v1/models/my_model:predict'
headers = {"content-type": "application/json"}
response = requests.post(url, data=json_request, headers=headers)

# Step 6: Print prediction results
print('Prediction response:', response.json())

Exported the trained Keras model to TensorFlow SavedModel format for serving compatibility.

Used TensorFlow Serving Docker container to serve the model on port 8501.

Prepared input data as JSON and sent it via REST API to the serving endpoint.

Received and printed the prediction results from the server.

Results Interpretation

Before: Model was saved but not accessible for real-time predictions.

After: Model is served via TensorFlow Serving REST API and returns predictions on input data.

This experiment shows how to deploy a TensorFlow model for real-time use by exporting it properly and using TensorFlow Serving. Serving enables applications to get predictions efficiently without retraining or embedding the model.

Bonus Experiment

Try serving the model using gRPC API instead of REST API and compare the latency.

💡 Hint

Use TensorFlow Serving gRPC client libraries and test with the same input data to measure response time differences.

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