Autoencoder for images in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the necessary library for building a neural network model.

Computer Vision

from tensorflow import [1]

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

Akeras

Bmatplotlib

Cnumpy

Dpandas

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated libraries like pandas or matplotlib.

Forgetting to import keras from tensorflow.

The keras module from TensorFlow is used to build neural network models including autoencoders.

2fill in blank

medium

Complete the code to define the input shape for the autoencoder model.

Computer Vision

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

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

A(28, 28, 1)

B(100,)

C(3, 224, 224)

D(None,)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a flat vector shape like (100,) instead of image dimensions.

Using color image shape (3, 224, 224) which is incorrect here.

The input shape for grayscale images of size 28x28 pixels is (28, 28, 1).

3fill in blank

hard

Fix the error in the code to compile the autoencoder model with the correct loss function.

Computer Vision

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

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

Aprecision

Bmse

Ccategorical_crossentropy

Daccuracy

Attempts:

3 left

💡 Hint

Common Mistakes

Using classification losses like categorical_crossentropy.

Using metrics like accuracy or precision as loss.

For autoencoders reconstructing images, the mean squared error (mse) loss is commonly used.

4fill in blank

hard

Fill both blanks to create the encoder part of the autoencoder using convolution and pooling layers.

Computer Vision

x = keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same')(input_img)
x = keras.layers.[1]((2, 2), padding='same')(x)

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

AFlatten

BDense

CDropout

DMaxPooling2D

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense or Flatten layers directly after Conv2D in encoder.

Using Dropout which is for regularization, not pooling.

The encoder uses Conv2D followed by MaxPooling2D to reduce image size while extracting features.

5fill in blank

hard

Fill all three blanks to build the decoder part with upsampling and convolution layers to reconstruct the image.

Computer Vision

x = keras.layers.[1]((2, 2))(encoded)
x = keras.layers.Conv2D(32, (3, 3), activation='relu', padding='[2]')(x)
decoded = keras.layers.Conv2D(1, (3, 3), activation='[3]', padding='same')(x)

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

AMaxPooling2D

Bsame

Csigmoid

DUpSampling2D

Attempts:

3 left

💡 Hint

Common Mistakes

Using MaxPooling2D in decoder which reduces size instead of increasing.

Using relu activation in output layer instead of sigmoid.

The decoder upsamples the encoded features using UpSampling2D, then applies convolution with same padding and a sigmoid activation to reconstruct the image pixels between 0 and 1.

Practice

1. What is the main purpose of an autoencoder when applied to images?

easy

A. To generate new images from random noise

B. To classify images into categories

C. To compress and then reconstruct the image data

D. To detect edges using filters

Solution

1. Step 1: Understand autoencoder function

   An autoencoder learns to compress input data into a smaller representation and then reconstruct it back.

2. Step 2: Apply to images

   For images, this means compressing image pixels and reconstructing the image to learn important features.

3. Final Answer:

   To compress and then reconstruct the image data -> Option C

4. Quick Check:

   Autoencoder = compression + reconstruction [OK]

Hint: Autoencoder = compress + rebuild images [OK]

Common Mistakes:

• Confusing autoencoder with classifier
• Thinking autoencoder generates new images
• Mixing edge detection with autoencoding

2. Which of the following is the correct way to define the encoder part of a convolutional autoencoder in Python using Keras?

easy

A. encoder = Sequential([LSTM(32, input_shape=(28,28,1))])

B. encoder = Sequential([Dense(32, activation='relu', input_shape=(28,28,1))])

C. encoder = Sequential([Conv1D(32, 3, activation='relu', input_shape=(28,28,1))])

D. encoder = Sequential([Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)), MaxPooling2D((2,2))])

Solution

1. Step 1: Identify convolutional layers for images

   Conv2D layers are used for 2D image data, with filters and kernel size.

2. Step 2: Check correct syntax and input shape

   encoder = Sequential([Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)), MaxPooling2D((2,2))]) uses Conv2D with activation and input shape for grayscale images (28x28x1), plus pooling for downsampling.

3. Final Answer:

   encoder = Sequential([Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)), MaxPooling2D((2,2))]) -> Option D

4. Quick Check:

   Conv2D + MaxPooling2D = convolutional encoder [OK]

Hint: Use Conv2D for images, not Dense or Conv1D [OK]

Common Mistakes:

• Using Dense layer instead of Conv2D for images
• Using Conv1D which is for sequences, not images
• Using LSTM which is for sequences, not images

3. Given this simple convolutional autoencoder code snippet, what will be the shape of the encoded output?

from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D
from tensorflow.keras.models import Model
input_img = Input(shape=(28, 28, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
encoded = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
model = Model(input_img, encoded)

medium

A. (14, 14, 8)

B. (28, 28, 8)

C. (7, 7, 8)

D. (14, 14, 16)

Solution

1. Step 1: Analyze input and first Conv2D layer

   Input shape is (28,28,1). First Conv2D with padding='same' keeps spatial size (28,28), output channels 16.

2. Step 2: Apply MaxPooling2D with pool size (2,2) and padding='same'

   This halves spatial dimensions: (28,28) -> (14,14), channels remain 16.

3. Step 3: Apply second Conv2D with 8 filters and padding='same'

   Spatial size stays (14,14), channels become 8.

4. Final Answer:

   (14, 14, 8) -> Option A

5. Quick Check:

   Pooling halves size, Conv2D changes channels [OK]

Hint: Pooling halves size, Conv2D changes channels [OK]

Common Mistakes:

• Ignoring padding='same' effect on size
• Assuming Conv2D changes spatial size
• Confusing channels with spatial dimensions

4. You wrote this decoder code for your convolutional autoencoder but get an error during training:

decoder = Sequential([
  Conv2D(8, (3,3), activation='relu', padding='same', input_shape=(14,14,16)),
  UpSampling2D((2,2)),
  Conv2D(1, (3,3), activation='sigmoid', padding='same')
])

What is the likely cause of the error?

medium

A. Missing UpSampling2D layer before the last Conv2D

B. Input shape to decoder does not match encoded output shape

C. Activation 'sigmoid' is not allowed in Conv2D

D. Conv2D filters must be 16, not 8 or 1

Solution

1. Step 1: Check encoded output shape

   The encoder output shape is (14,14,8) after the final Conv2D layer, but decoder input shape=(14,14,16).

2. Step 2: Verify decoder input shape matches encoded output

   Decoder input_shape=(14,14,16) does not match encoded output (14,14,8), causing shape mismatch in channels during training.

3. Step 3: Identify common error cause

   Often error arises if decoder input shape does not match encoder output shape exactly, causing shape mismatch during training.

4. Final Answer:

   Input shape to decoder does not match encoded output shape -> Option B

5. Quick Check:

   Decoder input shape must match encoder output [OK]

Hint: Decoder input shape must match encoder output shape [OK]

Common Mistakes:

• Thinking activation 'sigmoid' is invalid
• Assuming filters must be 16 always
• Ignoring input shape mismatch errors

5. You want to use a convolutional autoencoder to remove noise from grayscale images of size 64x64. Which architecture choice is best to preserve spatial details while reducing noise?

hard

A. Use multiple Conv2D layers with small (3x3) kernels and padding='same', plus MaxPooling2D for downsampling

B. Use Dense layers only to compress the flattened image vector

C. Use Conv1D layers with large kernels to capture noise patterns

D. Use a single Conv2D layer without pooling or upsampling

Solution

1. Step 1: Understand noise removal with autoencoders

   Noise removal requires learning spatial features and reconstructing clean images, so preserving spatial info is key.

2. Step 2: Evaluate architecture choices

   Multiple Conv2D layers with small kernels and padding='same' keep spatial size and details; MaxPooling2D reduces size to learn compressed features.

3. Step 3: Reject other options

   Dense layers lose spatial info; Conv1D is for sequences; single Conv2D without pooling won't compress well.

4. Final Answer:

   Use multiple Conv2D layers with small (3x3) kernels and padding='same', plus MaxPooling2D for downsampling -> Option A

5. Quick Check:

   Conv2D + pooling preserves spatial details for denoising [OK]

Hint: Use Conv2D + pooling to keep spatial info and reduce noise [OK]

Common Mistakes:

• Using Dense layers losing image structure
• Using Conv1D which is for 1D data
• Skipping pooling reduces compression ability