AI Capstone Project with Deep Learning Quiz Answers

AI Capstone Project with Deep Learning Week 01 Quiz Answers

Quiz 01: Download Data

Q1. For question one what was the correct answer for the output of the positive directory

• [‘/resources/data/Positive/00001.jpg’, ‘/resources/data/Positive/00002.jpg’, ‘/resources/data/Positive/00003.jpg’]
• [‘00001.jpg’, ‘0002.jpg’, ‘00003.jpg’]
• [‘/resources/data/Negative/00001.jpg’, ‘/resources/data/Negative/00002.jpg’, ‘/resources/data/Negative/00003.jpg’]

Q2. What is the correct plot for the first three images with cracks:

• there is no output

Quiz 02: Loading Data with Keras

Q1. Which of the following represents the right dimensions of the images in the dataset?

• (224, 224, 3)
• (227, 227, 1)
• (220, 220, 3)
• (227, 227, 3)
• (211, 211, 3)

Q2. According to the lab, how many images belonging to the negative class exist in the dataset?

• 10,000 images.
• 15,000 images.
• 40,000 images.
• 5,000 images.
• 20,000 images.

Q3. According to the lab, which of the following shows images 2 – 5 in the ./Negative directory according to the iterator what we defined in the lab?

Q4. According to the lab, how many images belonging to the positive class exist in the dataset?

• 20,000 images.
• 10,000 images.
• 5,000 images.
• 15,000 images.
• 40,000 images.

Q5. According to the lab, which of the following show the first four images in the ./Positive directory?

AI Capstone Project with Deep Learning Week 02 Quiz Answers

Quiz 01: Data loader PyTorch

Q1. How many total Samples are in the dataset

• Enter Answer here

Q2. Select the correct output from lab two question two. That even indexes contain the path to images with positive or cracked samples and the odd element contains the negative images or images without cracks. Make sure you sort the output.

Q3. From Lab 2 question 3 select the correct image that represents the first four elements of the validation data.

Q4. From Lab 2 Question 4 displays sample 9 and sample 100 from the training dataset using the appropriate object.

Q5. From Lab 2 Question 5 displays sample 15 and sample 102 from the validation dataset

Quiz 02: Data Preparation with Keras

Q1. From the lab, how many images was the ImageDataGenerator able to fetch from the directory ./concrete_data_week2?

• 20,000 images.
• 400,000 images.
• 40,000 images.
• 2000 images.

Q2. Using a random seed of 24 and for a batch size of 4 images, which of the following represents the images in the third batch of the ImageDataGenerator object defined on the entire dataset?

Q3. How many images from each class are in the fourth batch?

• 4 positive images.
• 3 positive images and 1 negative image.
• 3 negative images and 1 positive image.
• 2 positive images and 2 negative images.
• 4 negative images

Q4. Using a random seed of 24 and for a batch size of 4 images, which of the following represents the second image in the fifth batch of the ImageDataGenerator object defined on the entire dataset?

Q5. How many images from each class are in the fifth batch?

• 4 negative images.
• 2 positive images and 2 negative images.
• 3 negative images and 1 positive image.
• 4 positive images.
• 3 positive images and 1 negative image.

AI Capstone Project with Deep Learning Week 03 Quiz Answers

Quiz 01: Linear Classifier PyTorch

Q1. What was the highest approximate validation accuracy:

• approximately 50%
• approximately 60%
• approximately 70%

Quiz 02: Building a Classifier with Pre-Trained Models

Q1. According to the lab, how many parameters did the ResNet50 pre-trained model have?

• 50 parameters.
• 23,591,810 parameters.
• 175 parameters.
• 4,098 parameters.
• 23,587,712 parameters.

Q2. According to the lab, how many images were used for training?

• 15,000 images.
• 20,000 images.
• 30,000 images.
• 10,000 images.
• 25,000 images.

Q3. According to the lab, how many images were used for validation?

• 20,000 images.
• 1,000 images.
• 5,000 images.
• 10,000 images.
• 15,000 images.

Q4. According to the lab, which of the following was the correct code to define an ImageDataGenerator for the validation set?

• .

data_generator = ImageDataGenerator(
    preprocessing_function=preprocess_input,
)

validation_generator = data_generator.flow_from_directory(
    'concrete_data_week3/train',
    target_size=(224, 224),
    batch_size=100,
    class_mode='categorical')

• .

data_generator = ImageDataGenerator(
    preprocessing_function=preprocess_input,
)

validation_generator = data_generator.flow_from_directory(
    'concrete_data_week3/valid',
    target_size=(224, 224),
    batch_size=100,
    class_mode='categorical')

• .

data_generator = ImageDataGenerator(
    preprocessing_function=preprocess_input,
)

validation_generator = data_generator.flow_from_dataframe(
    'concrete_data_week3/valid',
    target_size=(224, 224),
    batch_size=100,
    class_mode='categorical')

• .

data_generator = ImageDataGenerator(
    preprocessing_function=preprocess_input,
)

validation_generator = data_generator.flow_from_directory(
    'concrete_data_week3/valid',
    target_size=(227, 227),
    batch_size=100,
    class_mode='categorical')

Q5. What method is used to fit a model on batches from an ImageDataGenerator?

• fit_generator
• fit
• flow_from_directory
• apply_transform
• flow

Get all Course Quiz Answers for IBM AI Engineering Professional Certificate

Machine Learning with Python Coursera Quiz Answers

Introduction to Deep Learning & Neural Networks with Keras Quiz Answers

Introduction to Computer Vision and Image Processing Quiz Answers

Deep Neural Networks with PyTorch Coursera Quiz Answers

Building Deep Learning Models with TensorFlow Coursera Quiz Answers

AI Capstone Project with Deep Learning Coursera Quiz Answers