Model serving (TF Serving) in TensorFlow - Model Pipeline Trace

Model Pipeline - Model serving (TF Serving)

This pipeline shows how a trained TensorFlow model is prepared and served using TensorFlow Serving. It starts with a trained model, then exports it, loads it into the serving system, and finally handles prediction requests from users.

Data Flow - 4 Stages

1Trained Model Export

1000 rows x 10 features→Save trained TensorFlow model in SavedModel format→SavedModel directory with model files

Model saved at /models/my_model/1/ with variables and assets

↓

2Model Loading in TF Serving

SavedModel directory→TensorFlow Serving loads the SavedModel into memory→Model ready to serve with input shape 10 features

TF Serving loads model version 1 and listens on port 8501

↓

3Prediction Request

1 row x 10 features (JSON input)→Client sends input data via REST API to TF Serving→Prediction output JSON with probabilities or values

{"instances": [[0.5, 1.2, ..., 0.3]]} sent to /v1/models/my_model:predict

↓

4Prediction Response

Model input processed internally→Model computes prediction and returns result→JSON with prediction results

{"predictions": [[0.1, 0.9]]} indicating class probabilities

Training Trace - Epoch by Epoch

Loss
0.7 |*       
0.6 | *      
0.5 |  *     
0.4 |   *    
0.3 |    *   
0.2 |     *  
0.1 |      * 
    +--------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning with moderate loss and accuracy
2	0.48	0.75	Loss decreases and accuracy improves as model learns
3	0.35	0.85	Model shows good learning progress
4	0.28	0.90	Loss continues to decrease, accuracy nearing high value
5	0.22	0.93	Training converges with low loss and high accuracy

Prediction Trace - 3 Layers

Layer 1: Input Reception

Layer 2: Model Inference

Layer 3: Output Formatting

Model Quiz - 3 Questions

What format does TensorFlow Serving expect the trained model to be saved in?

A SavedModel format

B CSV file

C Pickle file

D JSON file

Key Insight

Model serving with TensorFlow Serving allows a trained model to be efficiently loaded and respond to prediction requests in real time. The pipeline ensures the model is saved in a standard format, loaded into a server, and can handle input/output transformations automatically for easy integration.

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