Why generative models create new data in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the TensorFlow library.

TensorFlow

import [1] as tf

Drag options to blanks, or click blank then click option'

Atensorflow

Btorch

Cnumpy

Dsklearn

Attempts:

3 left

💡 Hint

Common Mistakes

Importing torch instead of tensorflow.

Using numpy or sklearn which are not for deep learning models.

TensorFlow is imported as tf to use its functions for building generative models.

2fill in blank

medium

Complete the code to define a simple generator model using Keras Sequential API.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(128, activation='relu', input_shape=(100,)),
    tf.keras.layers.Dense(784, activation=[1])
])

Drag options to blanks, or click blank then click option'

A'softmax'

B'relu'

C'sigmoid'

D'tanh'

Attempts:

3 left

💡 Hint

Common Mistakes

Using softmax activation which is for classification tasks.

Using relu or tanh which can produce values outside 0-1 range.

The output layer uses sigmoid activation to generate pixel values between 0 and 1 for new image data.

3fill in blank

hard

Fix the error in the code to compile the generator model with binary crossentropy loss.

TensorFlow

model.compile(optimizer='adam', loss=[1])

Drag options to blanks, or click blank then click option'

A'binary_crossentropy'

B'mean_squared_error'

C'categorical_crossentropy'

D'hinge'

Attempts:

3 left

💡 Hint

Common Mistakes

Using categorical crossentropy which expects one-hot labels.

Using mean squared error which is less common for binary outputs.

Binary crossentropy loss is used for generative models producing binary or normalized outputs.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps noise vectors to generated images.

TensorFlow

generated_images = {noise: model([1]) for noise in noises if noise.shape[0] [2] 100}

Drag options to blanks, or click blank then click option'

Atf.expand_dims(noise, 0)

Bnoise

C==

D>

Attempts:

3 left

💡 Hint

Common Mistakes

Passing noise directly without expanding dims causes shape errors.

Using equality instead of greater than in the condition.

Noise vectors are expanded to add batch dimension before passing to the model. We filter noises with batch size greater than 100.

5fill in blank

hard

Fill all three blanks to create a function that generates new data from random noise using the generator model.

TensorFlow

def generate_new_data(model, [1]):
    noise = tf.random.normal(shape=([2], 100))
    generated = model([3])
    return generated

Drag options to blanks, or click blank then click option'

Anum_samples

Cnoise

Dnum_samples * 100

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong variable names or shapes for noise.

Passing incorrect input to the model.

The function takes the number of samples, creates noise vectors of that size, passes noise to the model, and returns generated data.

Practice

1. Why do generative models create new data in machine learning?

easy

A. To only classify existing data into categories

B. To delete old data from the dataset

C. To learn patterns from existing data and generate similar new data

D. To speed up data collection from the internet

Solution

1. Step 1: Understand generative model purpose

   Generative models learn from existing data patterns to create new, similar data.

2. Step 2: Eliminate incorrect options

   Deleting data, classifying data, or speeding data collection are not goals of generative models.

3. Final Answer:

   To learn patterns from existing data and generate similar new data -> Option C

4. Quick Check:

   Generative models create new data by learning patterns = C [OK]

Hint: Generative models imitate data patterns to create new data [OK]

Common Mistakes:

• Confusing generative models with classifiers
• Thinking generative models delete data
• Assuming generative models only speed up data collection

2. Which TensorFlow code snippet correctly defines a simple generative model layer?

easy

A. tf.keras.layers.Dense(units=128, activation='relu')

B. tf.keras.layers.Conv2D(filters=32, kernel_size=3)

C. tf.keras.layers.Dropout(rate=0.5)

D. tf.keras.layers.MaxPooling2D(pool_size=2)

Solution

1. Step 1: Identify generative model layer type

   Dense layers with activation functions are commonly used in generative models to create outputs.

2. Step 2: Check other layers' roles

   Conv2D is for feature extraction, Dropout for regularization, MaxPooling2D for downsampling, not direct generation.

3. Final Answer:

   tf.keras.layers.Dense(units=128, activation='relu') -> Option A

4. Quick Check:

   Dense layer with activation is used in generative models = A [OK]

Hint: Dense layers with activation create new data features [OK]

Common Mistakes:

• Choosing convolution layers as generative output
• Confusing dropout with data generation
• Selecting pooling layers for generation

3. Given this TensorFlow code snippet for a simple generative model, what is the shape of the output tensor?

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Dense(64, activation='relu', input_shape=(100,)),
  tf.keras.layers.Dense(28*28, activation='sigmoid'),
  tf.keras.layers.Reshape((28, 28))
])
output = model(tf.random.normal([1, 100]))
print(output.shape)

medium

A. (28, 28)

B. (100, 28, 28)

C. (1, 784)

D. (1, 28, 28)

Solution

1. Step 1: Analyze model layers and input

   Input shape is (100,), first Dense outputs 64 units, second Dense outputs 28*28=784 units, then reshaped to (28, 28).

2. Step 2: Check batch size and output shape

   Input batch size is 1, so output shape after reshape is (1, 28, 28).

3. Final Answer:

   (1, 28, 28) -> Option D

4. Quick Check:

   Output shape matches batch and reshape = (1, 28, 28) [OK]

Hint: Remember batch size stays in output shape [OK]

Common Mistakes:

• Ignoring batch size dimension
• Confusing flattened and reshaped output
• Assuming output shape is (28, 28) without batch

4. This TensorFlow code tries to generate new images but throws an error. What is the problem?

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Dense(64, activation='relu', input_shape=(100,)),
  tf.keras.layers.Dense(28*28, activation='sigmoid'),
  tf.keras.layers.Reshape((28, 28))
])
noise = tf.random.normal([100, 28])
output = model(noise)
print(output.shape)

medium

A. Input batch size should be first dimension, so shape should be (batch_size, 100), not (100, 28)

B. Activation function 'sigmoid' is not allowed in generative models

C. Reshape layer cannot reshape to (28, 28)

D. Dense layers require integer inputs, not float tensors

Solution

1. Step 1: Analyze model input expectation

   The model has input_shape=(100,), so expects inputs of shape (batch_size, 100).

2. Step 2: Check provided input shape

   noise = tf.random.normal([100, 28]) has shape (100, 28), where the feature dimension is 28 instead of 100, causing a shape mismatch error.

3. Final Answer:

   Input batch size should be first dimension, so shape should be (batch_size, 100), not (100, 28) -> Option A

4. Quick Check:

   Model input_shape=(100,) requires feature dim=100; got 28 [OK]

Hint: Batch size is always first dimension in TensorFlow inputs [OK]

Common Mistakes:

• Mixing up batch size and feature dimensions
• Thinking activation functions cause errors
• Assuming reshape layer is invalid without checking

5. You want to build a generative model in TensorFlow that creates new handwritten digits similar to MNIST data. Which approach best explains why the model can create new images?

hard

A. The model memorizes all MNIST images and randomly picks one to output

B. The model learns the distribution of pixel patterns from MNIST and samples new points from this learned distribution

C. The model uses a fixed noise input and outputs the same image every time

D. The model only classifies digits and does not generate new images

Solution

1. Step 1: Understand generative model learning

   The model learns the underlying distribution of the training data (pixel patterns) to generate new samples.

2. Step 2: Eliminate incorrect options

   Memorizing images means no new data; fixed noise gives same output; classification does not generate data.

3. Final Answer:

   The model learns the distribution of pixel patterns from MNIST and samples new points from this learned distribution -> Option B

4. Quick Check:

   Generative models sample new data from learned distribution = A [OK]

Hint: Generative models sample new data from learned patterns [OK]

Common Mistakes:

• Thinking generative models memorize data
• Assuming fixed noise means varied output
• Confusing classification with generation