Image datasets (CIFAR-10, ImageNet) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the CIFAR-10 dataset using TensorFlow.

Computer Vision

import tensorflow as tf
(cifar_train, cifar_test) = tf.keras.datasets.cifar10.[1]()

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

Aload_data

Bfetch

Cdownload

Dget_dataset

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'download' or 'fetch' which are not valid TensorFlow dataset methods.

Trying to call a method that does not exist in tf.keras.datasets.cifar10.

The correct function to load CIFAR-10 dataset in TensorFlow is load_data(). It returns training and test sets.

2fill in blank

medium

Complete the code to normalize CIFAR-10 images to the range 0-1.

Computer Vision

cifar_train_images = cifar_train[0] / [1]

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

A255

B100

C1

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Dividing by 100 or 256 which does not correctly normalize pixel values.

Not dividing at all, leaving pixel values in 0-255 range.

Image pixel values range from 0 to 255. Dividing by 255 scales them to 0-1.

3fill in blank

hard

Fix the error in this code to load ImageNet dataset using TensorFlow Datasets.

Computer Vision

import tensorflow_datasets as tfds
imagenet_data = tfds.load('imagenet_v2', split=[1])

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

A'train[:80%]'

B'validation'

C'train'

D'test'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' or 'test' which may not exist or are not the validation split.

Using slicing syntax like 'train[:80%]' which is invalid here.

The ImageNet dataset split for validation is named 'validation'. Using 'validation' loads the validation set correctly.

4fill in blank

hard

Fill both blanks to create a dictionary of image shapes and labels from CIFAR-10 training data.

Computer Vision

image_info = {i: {'shape': cifar_train[0][i].[1], 'label': cifar_train[1][i][[2]]} for i in range(5)}

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

Ashape

B0

C1

Dsize

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'size' instead of 'shape' for image dimensions.

Using label index 1 which is out of range.

Each image has a shape attribute for its dimensions. Labels are stored as arrays, so index 0 accesses the label value.

5fill in blank

hard

Fill all three blanks to filter CIFAR-10 images with width greater than 30 and create a dictionary of their labels and shapes.

Computer Vision

filtered = {i: {'label': cifar_train[1][i][0], 'shape': cifar_train[0][i].[1] for i in range(len(cifar_train[0])) if cifar_train[0][i].shape[[2]] [3] 30}

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

Ashape

B1

C>

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using index 0 which is height, not width.

Using '<' instead of '>' for filtering.

The image shape attribute gives dimensions. Index 1 corresponds to width. We filter images with width greater than 30 using '>'.

Practice

1. Which of the following best describes the CIFAR-10 dataset?

easy

A. A small dataset with 10 classes of images, easy for beginners

B. A very large dataset with millions of images and thousands of classes

C. A dataset mainly used for text recognition tasks

D. A dataset containing only black and white images

Solution

1. Step 1: Understand CIFAR-10 size and classes

   CIFAR-10 contains 60,000 small images divided into 10 classes, making it manageable for beginners.

2. Step 2: Compare with other datasets

   ImageNet is much larger with many more classes, unlike CIFAR-10.

3. Final Answer:

   A small dataset with 10 classes of images, easy for beginners -> Option A

4. Quick Check:

   CIFAR-10 = small, 10 classes [OK]

Hint: Remember CIFAR-10 is small and simple for learning [OK]

Common Mistakes:

• Confusing CIFAR-10 with ImageNet size
• Thinking CIFAR-10 has many classes
• Assuming CIFAR-10 is for text data

2. Which Python code correctly loads the CIFAR-10 dataset using TensorFlow?

easy

A. import cifar10
train_images, train_labels = cifar10.load()

B. from tensorflow.keras.datasets import cifar10
(train_images, train_labels), (test_images, test_labels) = cifar10.load_data()

C. from tensorflow.data import cifar10
train, test = cifar10.load()

D. from keras.datasets import imagenet
train, test = imagenet.load_data()

Solution

1. Step 1: Identify correct import for CIFAR-10 in TensorFlow

   The correct import is from tensorflow.keras.datasets import cifar10.

2. Step 2: Check the loading function

   cifar10.load_data() returns training and testing sets as tuples.

3. Final Answer:

   from tensorflow.keras.datasets import cifar10 (train_images, train_labels), (test_images, test_labels) = cifar10.load_data() -> Option B

4. Quick Check:

   Correct import and load_data() method [OK]

Hint: Use tensorflow.keras.datasets for CIFAR-10 loading [OK]

Common Mistakes:

• Using wrong module names like tensorflow.data
• Trying to load ImageNet with CIFAR-10 code
• Missing the load_data() function call

3. What will be the shape of the training images array after loading CIFAR-10 with TensorFlow?

medium

A. (100000, 64, 64, 3)

B. (60000, 28, 28, 1)

C. (50000, 32, 32, 3)

D. (50000, 224, 224, 3)

Solution

1. Step 1: Recall CIFAR-10 image count and size

   CIFAR-10 has 50,000 training images, each 32x32 pixels with 3 color channels (RGB).

2. Step 2: Match shape format

   The shape is (number_of_images, height, width, channels) = (50000, 32, 32, 3).

3. Final Answer:

   (50000, 32, 32, 3) -> Option C

4. Quick Check:

   Training images shape = (50000, 32, 32, 3) [OK]

Hint: CIFAR-10 images are 32x32 RGB, 50k training samples [OK]

Common Mistakes:

• Confusing CIFAR-10 with MNIST image size
• Using ImageNet image dimensions
• Mixing training and test set sizes

4. You wrote this code to load ImageNet but get an error:

from tensorflow.keras.datasets import imagenet
(train_images, train_labels), (test_images, test_labels) = imagenet.load_data()

What is the main problem?

medium

A. ImageNet is not available in tensorflow.keras.datasets module

B. The load_data() function requires extra parameters

C. You must import ImageNet from tensorflow.data instead

D. ImageNet images are grayscale, so loading fails

Solution

1. Step 1: Check TensorFlow dataset availability

   TensorFlow's keras.datasets does not include ImageNet; it includes CIFAR-10, MNIST, etc.

2. Step 2: Understand ImageNet loading method

   ImageNet requires special handling or external libraries, not keras.datasets.

3. Final Answer:

   ImageNet is not available in tensorflow.keras.datasets module -> Option A

4. Quick Check:

   ImageNet not in keras.datasets [OK]

Hint: ImageNet needs special loading, not keras.datasets [OK]

Common Mistakes:

• Assuming ImageNet loads like CIFAR-10
• Trying to import from wrong TensorFlow submodules
• Believing ImageNet images are grayscale

5. You want to train a model to recognize 1000 different object categories. Which dataset is best suited for this task?

hard

A. CIFAR-10, because it has 10 classes and is easy to use

B. Fashion-MNIST, because it has clothing images

C. MNIST, because it has handwritten digits

D. ImageNet, because it has 1000 classes and many images per class

Solution

1. Step 1: Identify dataset class count

   CIFAR-10 has only 10 classes, MNIST and Fashion-MNIST have 10 classes each, ImageNet has 1000 classes.

2. Step 2: Match dataset to task

   For recognizing 1000 categories, ImageNet is the suitable dataset due to its size and diversity.

3. Final Answer:

   ImageNet, because it has 1000 classes and many images per class -> Option D

4. Quick Check:

   1000 classes need ImageNet [OK]

Hint: Use ImageNet for many classes, CIFAR-10 for few [OK]

Common Mistakes:

• Choosing CIFAR-10 for many classes
• Confusing MNIST with ImageNet
• Ignoring class count importance