Model serving (TF Serving) in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Model serving (TF Serving)

Which metric matters for Model Serving (TF Serving) and WHY

When serving a model, the key metrics are latency, throughput, and prediction accuracy.

Latency measures how fast the model responds to a request. Low latency means users get results quickly.

Throughput measures how many requests the server can handle per second. High throughput means the system can serve many users at once.

Prediction accuracy ensures the model's predictions remain reliable after deployment.

We focus on these because serving is about delivering fast and correct predictions to users in real time.

Confusion Matrix Example for Model Serving

Suppose the served model is a binary classifier. Here is a confusion matrix from predictions on 100 samples:

      | Predicted Positive | Predicted Negative |
      |--------------------|--------------------|
      | True Positive (TP): 40 | False Negative (FN): 10 |
      | False Positive (FP): 5 | True Negative (TN): 45 |
    

Total samples = TP + FP + TN + FN = 40 + 5 + 45 + 10 = 100

Precision = TP / (TP + FP) = 40 / (40 + 5) = 0.89

Recall = TP / (TP + FN) = 40 / (40 + 10) = 0.80

F1 Score = 2 * (Precision * Recall) / (Precision + Recall) ≈ 0.84

Precision vs Recall Tradeoff in Model Serving

Imagine a spam detection model served to users:

• High Precision: Few good emails are wrongly marked as spam. Users don't miss important emails.
• High Recall: Most spam emails are caught. Users see less spam.

In serving, if the model has low precision, users get annoyed by false spam. If recall is low, spam slips through.

Choosing the right balance depends on user needs and business goals.

Good vs Bad Metric Values for Model Serving

Good:

• Latency under 100 milliseconds for real-time apps.
• Throughput that matches expected user load (e.g., 1000 requests/second).
• Accuracy metrics (precision, recall) above 80% for critical tasks.

Bad:

• Latency over 1 second causing user frustration.
• Throughput too low, causing request delays or failures.
• Accuracy metrics below 50%, meaning predictions are often wrong.

Common Metrics Pitfalls in Model Serving

• Ignoring latency: A model with great accuracy but slow response hurts user experience.
• Overfitting: High accuracy on training data but poor real-world performance after serving.
• Data leakage: Serving with outdated or biased data can mislead metrics.
• Not monitoring: Metrics can degrade over time if the model or data changes.

Self Check: Your model has 98% accuracy but 12% recall on fraud. Is it good?

No, it is not good for fraud detection.

High accuracy can be misleading if most transactions are not fraud. The model misses 88% of fraud cases (low recall), which is dangerous.

For fraud, recall is critical to catch as many frauds as possible, even if precision is lower.

Key Result

In model serving, low latency and high throughput ensure fast, scalable predictions, while precision and recall confirm prediction quality.

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