Prediction and evaluation in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of making predictions with a trained machine learning model?

Predictions are used to apply the learned patterns from training data to new, unseen data. This helps us make decisions or understand new inputs based on what the model has learned.

beginner

What does the 'evaluate' method in TensorFlow models do?

The 'evaluate' method calculates how well the model performs on test data by computing metrics like loss and accuracy. It helps us understand if the model generalizes well to new data.

beginner

Why is it important to use separate data for training and evaluation?

Using separate data prevents the model from just memorizing the training examples. It ensures the model can make good predictions on new data, showing it has truly learned patterns.

beginner

In TensorFlow, what does the 'predict' method return?

The 'predict' method returns the model's output for the input data, such as class probabilities or continuous values, depending on the task.

beginner

What is 'loss' in model evaluation?

Loss is a number that shows how far the model's predictions are from the true answers. Lower loss means better predictions.

What does the 'evaluate' method in TensorFlow return?

A Training data samples

B Loss and metrics values on test data

C Model architecture summary

D Predicted labels for input data

The 'evaluate' method returns loss and metric values computed on the test data to assess model performance.

Why should you not use training data to evaluate your model?

A Because evaluation requires labeled data

B Because training data is too small

C Because training data is always noisy

D Because it can cause the model to memorize and not generalize

Using training data for evaluation can cause overfitting, where the model memorizes training examples and performs poorly on new data.

What does the 'predict' method output in a classification task?

A Class probabilities or predicted classes

B Loss value

C Training accuracy

D Model weights

In classification, 'predict' outputs probabilities or predicted class labels for the input data.

Which metric is commonly used to measure model error during evaluation?

A Loss

B Learning rate

C Epoch count

D Batch size

Loss measures how far predictions are from true values and is used to evaluate model error.

What is the main goal of model evaluation?

A To change model architecture

B To increase training speed

C To check model performance on new data

D To generate training data

Model evaluation checks how well the model performs on data it has not seen before.

Explain how you would use a TensorFlow model to make predictions and then evaluate its performance on new data.

Think about the steps after training: first get predictions, then check how good they are.

Describe why separating data into training and evaluation sets is important in machine learning.

Consider what happens if the model sees the same data for both training and testing.