Monitoring deployed models in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Monitoring deployed models

Which metric matters for monitoring deployed models and WHY

When a model is deployed, we want to check if it keeps working well over time. Key metrics include accuracy, precision, recall, and F1 score. These show if the model still predicts correctly. We also watch data drift and prediction distribution to see if new data looks different from training data. This helps catch problems early.

Confusion matrix example for deployed model monitoring

      Actual \ Predicted | Positive | Negative
      -------------------|----------|---------
      Positive           |    85    |   15    
      Negative           |    10    |   90    

      Total samples = 85 + 15 + 10 + 90 = 200

      Precision = TP / (TP + FP) = 85 / (85 + 10) = 0.894
      Recall = TP / (TP + FN) = 85 / (85 + 15) = 0.85
      F1 Score = 2 * (Precision * Recall) / (Precision + Recall) ≈ 0.871
    

Precision vs Recall tradeoff with examples

Imagine a deployed email spam filter:

• High precision means most emails marked as spam really are spam. This avoids losing good emails.
• High recall means catching most spam emails, but might mark some good emails as spam.

Depending on user needs, we monitor which metric to keep balanced. If users complain about missing spam, increase recall. If they complain about losing good emails, increase precision.

What good vs bad metric values look like for monitoring

Good: Accuracy above 85%, precision and recall above 80%, stable over time.

Bad: Sudden drops in accuracy or recall, precision falling below 50%, or big changes in prediction patterns.

Good metrics mean the model still understands data well. Bad metrics warn us to retrain or fix the model.

Common pitfalls in monitoring deployed models

• Accuracy paradox: High accuracy but poor recall on important classes can hide problems.
• Data leakage: If monitoring data leaks future info, metrics look falsely good.
• Overfitting signs: Metrics suddenly perfect on monitoring data but bad in real use.
• Ignoring data drift: Not checking if new data differs from training data can cause unnoticed failures.

Self-check question

Your deployed fraud detection model has 98% accuracy but only 12% recall on fraud cases. Is it good for production? Why or why not?

Answer: No, it is not good. The model misses 88% of fraud cases (low recall), which is dangerous. High accuracy is misleading because fraud is rare. We need to improve recall to catch more fraud.

Key Result

Monitoring deployed models requires tracking accuracy, precision, recall, and data drift to ensure ongoing good performance.

Practice

1. What is the main purpose of monitoring deployed TensorFlow models?

easy

A. To reduce the model size

B. To check model health and accuracy over time

C. To train the model faster

D. To change the model architecture automatically

Solution

1. Step 1: Understand model deployment goals

   After deployment, models must be checked regularly to ensure they perform well and remain accurate.

2. Step 2: Identify monitoring purpose

   Monitoring focuses on tracking model health and accuracy, not training speed or size reduction.

3. Final Answer:

   To check model health and accuracy over time -> Option B

4. Quick Check:

   Monitoring = model health and accuracy check [OK]

Hint: Monitoring means checking model accuracy and health regularly [OK]

Common Mistakes:

• Confusing monitoring with training or model design
• Thinking monitoring changes model architecture
• Assuming monitoring reduces model size

2. Which TensorFlow tool is commonly used to define metrics and slices for monitoring deployed models?

easy

A. TensorFlow Model Analysis (tfma)

B. TensorFlow Lite

C. TensorBoard

D. TensorFlow Hub

Solution

1. Step 1: Identify tools for model monitoring

   TensorFlow Model Analysis (tfma) is designed to evaluate and monitor models by defining metrics and slices.

2. Step 2: Differentiate from other tools

   TensorBoard is for visualization, TensorFlow Lite is for mobile deployment, and TensorFlow Hub is for reusable model components.

3. Final Answer:

   TensorFlow Model Analysis (tfma) -> Option A

4. Quick Check:

   tfma = metrics and slices tool [OK]

Hint: tfma is for monitoring metrics and slices [OK]

Common Mistakes:

• Confusing TensorBoard with tfma
• Using TensorFlow Lite for monitoring
• Mixing TensorFlow Hub with monitoring tools

3. Given the code snippet below, what will be the output of the evaluation metrics?

import tensorflow_model_analysis as tfma

config = tfma.EvalConfig(
  model_specs=[tfma.ModelSpec(label_key='label')],
  metrics_specs=[tfma.MetricsSpec(metrics=[tfma.MetricConfig(class_name='ExampleCount')])]
)

result = tfma.run_model_analysis(
  eval_shared_model=tfma.default_eval_shared_model('model_dir'),
  eval_config=config,
  eval_input_receiver_fn=None
)

print(result.metrics['']['']['ExampleCount'])

medium

A. Error due to missing input_receiver_fn

B. Accuracy of the model

C. Loss value of the model

D. Total number of examples evaluated

Solution

1. Step 1: Analyze the code snippet

   The code calls tfma.run_model_analysis with eval_input_receiver_fn set to None, which is required for input data processing.

2. Step 2: Understand the impact of missing eval_input_receiver_fn

   Without a valid eval_input_receiver_fn, the evaluation cannot run properly and will raise an error.

3. Final Answer:

   Error due to missing input_receiver_fn -> Option A

4. Quick Check:

   Missing input_receiver_fn causes error [OK]

Hint: eval_input_receiver_fn cannot be None for evaluation [OK]

Common Mistakes:

• Assuming metrics print correctly without input_receiver_fn
• Confusing ExampleCount with accuracy or loss
• Ignoring required input functions in tfma

4. You run a TensorFlow Model Analysis job but notice the metrics are not updating after deployment. Which of the following is the most likely cause?

medium

A. The model was trained with too few epochs

B. The training data was too large

C. The model architecture changed after deployment

D. The evaluation job is not scheduled to run regularly

Solution

1. Step 1: Identify why metrics don't update

   If metrics don't update, it usually means the evaluation process is not running after deployment.

2. Step 2: Check scheduling of evaluation jobs

   Evaluation jobs must be scheduled regularly to monitor model performance over time.

3. Final Answer:

   The evaluation job is not scheduled to run regularly -> Option D

4. Quick Check:

   Regular evaluation runs update metrics [OK]

Hint: Schedule evaluation jobs regularly to update metrics [OK]

Common Mistakes:

• Blaming training epochs for monitoring issues
• Assuming architecture changes affect monitoring directly
• Thinking data size stops metric updates

5. You want to monitor a deployed TensorFlow model's performance on different user groups. Which approach best helps you achieve this using TensorFlow Model Analysis?

hard

A. Deploy multiple models without monitoring

B. Retrain the model separately for each user group

C. Define slices in tfma.EvalConfig to segment metrics by user group

D. Use TensorBoard to visualize overall accuracy only

Solution

1. Step 1: Understand slicing in tfma

   Slices allow monitoring metrics for specific data segments, such as user groups, to detect performance differences.

2. Step 2: Apply slices in EvalConfig

   By defining slices in tfma.EvalConfig, you can track metrics separately for each user group without retraining multiple models.

3. Final Answer:

   Define slices in tfma.EvalConfig to segment metrics by user group -> Option C

4. Quick Check:

   Slices segment metrics for groups [OK]

Hint: Use slices in tfma to monitor groups separately [OK]

Common Mistakes:

• Thinking retraining is needed for monitoring groups
• Using TensorBoard only for overall metrics
• Ignoring monitoring and deploying multiple models blindly