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.

Practice

1. What does the model.predict() function do in TensorFlow?

easy

A. It saves the model to a file

B. It trains the model on the data

C. It deletes the model from memory

D. It gives the model's guesses on new data

Solution

1. Step 1: Understand the purpose of model.predict()

   This function is used to get the model's output predictions for new input data after training.

2. Step 2: Differentiate from other functions

   Training uses model.fit(), saving uses model.save(), and deleting is manual memory management, none of which are predict().

3. Final Answer:

   It gives the model's guesses on new data -> Option D

4. Quick Check:

   model.predict() = model guesses [OK]

Hint: Predict means guess output for new inputs [OK]

Common Mistakes:

• Confusing predict() with fit() for training
• Thinking predict() saves the model
• Assuming predict() deletes the model

2. Which of the following is the correct way to evaluate a TensorFlow model on test data stored in X_test and y_test?

easy

A. model.score(X_test, y_test)

B. model.evaluate(X_test, y_test)

C. model.fit(X_test, y_test)

D. model.predict(X_test, y_test)

Solution

1. Step 1: Identify the evaluation function

   TensorFlow uses model.evaluate() to measure performance on test data.

2. Step 2: Check other options

   model.predict() makes predictions, model.fit() trains, and model.score() is not a TensorFlow method.

3. Final Answer:

   model.evaluate(X_test, y_test) -> Option B

4. Quick Check:

   Evaluate = measure performance [OK]

Hint: Use evaluate() to check model accuracy on test data [OK]

Common Mistakes:

• Using predict() instead of evaluate() for metrics
• Trying to train with evaluate()
• Using non-existent model.score() method

3. What will be the output of the following code snippet?

import tensorflow as tf
import numpy as np

model = tf.keras.Sequential([
  tf.keras.layers.Dense(1, input_shape=(1,))
])
model.compile(optimizer='sgd', loss='mse')

X = np.array([1, 2, 3, 4], dtype=float)
y = np.array([2, 4, 6, 8], dtype=float)

model.fit(X, y, epochs=10, verbose=0)
predictions = model.predict(np.array([5.0]))
print(predictions)

medium

A. A numpy array close to [[1.0]]

B. A numpy array close to [[5.0]]

C. A numpy array close to [[10.0]]

D. An error because input shape is wrong

Solution

1. Step 1: Understand the model and data

   The model is a simple linear layer trained to learn y = 2*x approximately.

2. Step 2: Predict for input 5.0

   After training, the model should predict close to 2*5 = 10, so output is near [[10.0]].

3. Final Answer:

   A numpy array close to [[10.0]] -> Option C

4. Quick Check:

   Prediction for 5 ≈ 10 [OK]

Hint: Model learns y=2x, predict(5) ≈ 10 [OK]

Common Mistakes:

• Expecting exact 10 instead of approximate
• Confusing input shape causing error
• Thinking prediction returns scalar, not array

4. You run model.evaluate(X_test, y_test) but get a ValueError about mismatched shapes. What is the most likely cause?

medium

A. The shapes of X_test and y_test do not match the model's expected input and output shapes

B. The model was not compiled before evaluation

C. The model.predict() function was called instead of evaluate()

D. The optimizer was set incorrectly

Solution

1. Step 1: Understand the error cause

   A ValueError about shape mismatch usually means input or output data shapes don't match what the model expects.

2. Step 2: Check other options

   Not compiling causes different errors, predict() vs evaluate() is unrelated, and optimizer issues cause training errors, not shape errors.

3. Final Answer:

   The shapes of X_test and y_test do not match the model's expected input and output shapes -> Option A

4. Quick Check:

   Shape mismatch causes ValueError in evaluate() [OK]

Hint: Check input/output shapes match model before evaluate() [OK]

Common Mistakes:

• Ignoring shape mismatch and blaming optimizer
• Confusing predict() with evaluate() errors
• Not compiling model but blaming shape error

5. You trained a model and want to compare its performance on two test sets: X_test1, y_test1 and X_test2, y_test2. Which approach correctly compares their accuracy using TensorFlow?

hard

A. Use model.evaluate() on both test sets separately and compare the returned loss or accuracy values

B. Use model.predict() on both test sets and compare the raw predictions directly

C. Train the model again on X_test2, y_test2 and compare training losses

D. Use model.fit() on both test sets and compare the final epoch losses

Solution

1. Step 1: Understand evaluation for performance

   model.evaluate() returns loss and metrics on test data without training, ideal for comparing performance.

2. Step 2: Why other options are incorrect

   Comparing raw predictions is not a direct accuracy measure; retraining or fitting on test sets changes the model and is not a fair comparison.

3. Final Answer:

   Use model.evaluate() on both test sets separately and compare the returned loss or accuracy values -> Option A

4. Quick Check:

   Evaluate test sets separately for fair comparison [OK]

Hint: Evaluate test sets separately, compare metrics [OK]

Common Mistakes:

• Comparing raw predictions without metrics
• Retraining on test data for comparison
• Using fit() on test data instead of evaluate()