Autoencoders in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the input layer for an autoencoder.

TensorFlow

input_img = tf.keras.Input(shape=[1])

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

A(28, 28, 1)

B(784,)

C(32, 32, 3)

D(10,)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a 3D shape like (28, 28, 1) instead of the flattened shape.

Using color image shape (32, 32, 3) for grayscale images.

The input shape for flattened 28x28 grayscale MNIST images is (784,), typical for simple Dense autoencoders.

2fill in blank

medium

Complete the code to add an encoding Dense layer with 64 units and ReLU activation.

TensorFlow

encoded = tf.keras.layers.Dense([1], activation='relu')(input_img)

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

A32

B128

C64

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Using too many units like 256 which is larger than input size.

Using too few units like 32 which might be too small for this example.

The encoding layer typically reduces dimensionality; here 64 units with ReLU activation is common.

3fill in blank

hard

Fix the error in the decoder layer to reconstruct the original input shape.

TensorFlow

decoded = tf.keras.layers.Dense([1], activation='sigmoid')(encoded)

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

A64

B128

C28

D784

Attempts:

3 left

💡 Hint

Common Mistakes

Using 64 units which is too small for reconstruction.

Using 28 units which is only one dimension of the input.

The decoder output layer should have the same number of units as the flattened input size (28*28=784) to reconstruct the image.

4fill in blank

hard

Fill both blanks to compile the autoencoder model with optimizer and loss function.

TensorFlow

autoencoder.compile(optimizer=[1], loss=[2])

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

A'adam'

B'sgd'

C'binary_crossentropy'

D'mse'

Attempts:

3 left

💡 Hint

Common Mistakes

Using SGD optimizer which may be slower to converge.

Using MSE loss which is also valid but less common for binary pixel data.

Adam optimizer and binary crossentropy loss are commonly used for autoencoders with normalized pixel values.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps words to their lengths if length is greater than 3.

TensorFlow

lengths = { [1] : [2] for [3] in words if len([3]) > 3 }

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

Aword

Blen(word)

Ditem

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'item' instead of 'word' as the loop variable.

Using the word itself as the value instead of its length.

The dictionary comprehension uses 'word' as key, 'len(word)' as value, and iterates over 'word' in words.

Practice

1. What is the main purpose of an autoencoder in machine learning?

easy

A. To compress data and then reconstruct it to learn important features

B. To classify images into categories

C. To generate new data from random noise

D. To sort data in ascending order

Solution

1. Step 1: Understand the role of autoencoders

   Autoencoders are designed to learn a compressed representation of data by encoding and then decoding it.

2. Step 2: Identify the main goal

   The goal is to capture important features by reconstructing the input data as closely as possible.

3. Final Answer:

   To compress data and then reconstruct it to learn important features -> Option A

4. Quick Check:

   Autoencoder purpose = compress and reconstruct [OK]

Hint: Autoencoders compress and rebuild data to learn features [OK]

Common Mistakes:

• Confusing autoencoders with classifiers
• Thinking autoencoders generate new random data
• Assuming autoencoders sort or label data

2. Which of the following is the correct way to define the encoder part of a simple autoencoder in TensorFlow using Keras Sequential API?

easy

A. encoder = tf.keras.Sequential([tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(784,))])

B. encoder = tf.keras.Sequential([tf.keras.layers.Dense(32, activation='softmax', input_shape=(784,))])

C. encoder = tf.keras.Sequential([tf.keras.layers.Dense(32, activation='relu', input_shape=(784,))])

D. encoder = tf.keras.Sequential([tf.keras.layers.Dense(32)])

Solution

1. Step 1: Check the layer type and activation

   The encoder should use a Dense layer with 'relu' activation for feature extraction.

2. Step 2: Verify input shape and activation correctness

   Input shape (784,) matches flattened input, and 'relu' is suitable for encoding.

3. Final Answer:

   encoder = tf.keras.Sequential([tf.keras.layers.Dense(32, activation='relu', input_shape=(784,))]) -> Option C

4. Quick Check:

   Dense + relu + correct input shape = encoder = tf.keras.Sequential([tf.keras.layers.Dense(32, activation='relu', input_shape=(784,))]) [OK]

Hint: Use Dense with relu and correct input shape for encoder [OK]

Common Mistakes:

• Using softmax activation in encoder
• Using Conv2D layer with flat input shape
• Omitting activation function

3. Given the following TensorFlow code for an autoencoder, what will be the shape of the encoded output?

import tensorflow as tf
input_layer = tf.keras.layers.Input(shape=(28, 28, 1))
flat = tf.keras.layers.Flatten()(input_layer)
encoded = tf.keras.layers.Dense(16, activation='relu')(flat)
model = tf.keras.Model(inputs=input_layer, outputs=encoded)

sample_input = tf.random.normal([10, 28, 28, 1])
encoded_output = model(sample_input)
print(encoded_output.shape)

medium

A. (16, 10)

B. (10, 28, 28, 1)

C. (10, 784)

D. (10, 16)

Solution

1. Step 1: Analyze input and flatten layer

   Input shape is (28, 28, 1), flatten converts it to (784,) per sample.

2. Step 2: Check Dense layer output size

   The Dense layer outputs 16 units, so output shape per sample is (16,).

3. Step 3: Consider batch size

   Batch size is 10, so final output shape is (10, 16).

4. Final Answer:

   (10, 16) -> Option D

5. Quick Check:

   Batch 10 x Dense 16 units = (10, 16) [OK]

Hint: Flatten input then Dense units define output shape [OK]

Common Mistakes:

• Confusing input shape with output shape
• Ignoring batch size dimension
• Assuming output shape matches input shape

4. You wrote this autoencoder training code but get a shape mismatch error:

autoencoder.compile(optimizer='adam', loss='mse')
autoencoder.fit(x_train, x_train.reshape(-1, 784), epochs=10)

What is the likely cause?

medium

A. Input and output shapes do not match during training

B. Loss function 'mse' is not suitable for autoencoders

C. Optimizer 'adam' cannot be used with autoencoders

D. Epochs value 10 is too low

Solution

1. Step 1: Check input and output shapes in fit()

   Input is x_train, output is x_train reshaped to (-1, 784), shapes differ if model expects original shape.

2. Step 2: Understand autoencoder training requirement

   Autoencoder input and output shapes must match; reshaping output differently causes mismatch.

3. Final Answer:

   Input and output shapes do not match during training -> Option A

4. Quick Check:

   Input/output shape mismatch causes error [OK]

Hint: Ensure input and output shapes match exactly during training [OK]

Common Mistakes:

• Changing output shape differently from input
• Blaming optimizer or loss function incorrectly
• Ignoring shape requirements in fit()

5. You want to build an autoencoder to denoise images. Which approach best fits this task?

hard

A. Train the autoencoder with clean images as input and noisy images as output

B. Train the autoencoder with noisy images as input and clean images as output

C. Train the autoencoder only on clean images without noise

D. Train the autoencoder with random noise as both input and output

Solution

1. Step 1: Understand denoising autoencoder goal

   Denoising autoencoders learn to remove noise by mapping noisy input to clean output.

2. Step 2: Choose training data setup

   Input should be noisy images, output should be corresponding clean images for learning noise removal.

3. Final Answer:

   Train the autoencoder with noisy images as input and clean images as output -> Option B

4. Quick Check:

   Denoising = noisy input, clean output [OK]

Hint: Noisy input, clean output trains denoising autoencoder [OK]

Common Mistakes:

• Swapping input and output roles
• Training only on clean images without noise
• Using random noise as output