You may download and use the CIFAR-10 dataset in keras using the following code: from keras.datasets import cifar10 (x_train, y_train), (x_test, y_test) cifar10.load data ()

Database System Concepts
7th Edition
ISBN:9780078022159
Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Chapter1: Introduction
Section: Chapter Questions
Problem 1PE
icon
Related questions
Question
Create a Convolutional Neural Network (CNN) in TensorFlow or keras to learn image classification
task using CIFAR-10 dataset. CIFAR-10 consists of 60000 32x32 color images in 10 classes, with 6000
images per class. There are 50000 training images and 10000 test images.
You may download and use the CIFAR-10 dataset in keras using the following code:
from keras.datasets import cifar10
(x_train, y_train), (x_test, y_test)
cifar10.load data ()
1) Create a 8-layer CNN as follows: CONV-POOL-CONV-POOL-CONV-POOL-FC-FC.
The CONV layers should use 3x3 filters with 32, 64 and 64 channels, stride of 1. The POOL layers
should use max 2x2 pooling with stride of 2. Calculate the total number of parameters for this
network.
Feel free to choose appropriate activation functions for the layers and justify your choice. Plot the
results and comment on the CNN performance.
2) Modify your CNN design as: CONV-CONV-POOL-CONV-POOL-FC-FC.
Use CONV layers of 5x5 filters (same number of channels as before), stride 1; POOL: 2x2, stride 2.
Calculate the total number of parameters in this network. Comment on the difference of number of
parameters with respect to the previous network. Plot the results and comment on the CNN
performance.
3) Modify your CNN design to achieve better accuracy than the previous two designs. You may
change the number of CONV and POOL layers, filter size, number of channels in each CONV layer,
strides, dropout etc. Justify your modifications and comment on the accuracy obtained.
Transcribed Image Text:Create a Convolutional Neural Network (CNN) in TensorFlow or keras to learn image classification task using CIFAR-10 dataset. CIFAR-10 consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. You may download and use the CIFAR-10 dataset in keras using the following code: from keras.datasets import cifar10 (x_train, y_train), (x_test, y_test) cifar10.load data () 1) Create a 8-layer CNN as follows: CONV-POOL-CONV-POOL-CONV-POOL-FC-FC. The CONV layers should use 3x3 filters with 32, 64 and 64 channels, stride of 1. The POOL layers should use max 2x2 pooling with stride of 2. Calculate the total number of parameters for this network. Feel free to choose appropriate activation functions for the layers and justify your choice. Plot the results and comment on the CNN performance. 2) Modify your CNN design as: CONV-CONV-POOL-CONV-POOL-FC-FC. Use CONV layers of 5x5 filters (same number of channels as before), stride 1; POOL: 2x2, stride 2. Calculate the total number of parameters in this network. Comment on the difference of number of parameters with respect to the previous network. Plot the results and comment on the CNN performance. 3) Modify your CNN design to achieve better accuracy than the previous two designs. You may change the number of CONV and POOL layers, filter size, number of channels in each CONV layer, strides, dropout etc. Justify your modifications and comment on the accuracy obtained.
Expert Solution
trending now

Trending now

This is a popular solution!

steps

Step by step

Solved in 2 steps

Blurred answer
Knowledge Booster
Types of trees
Learn more about
Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, computer-science and related others by exploring similar questions and additional content below.
Similar questions
  • SEE MORE QUESTIONS
Recommended textbooks for you
Database System Concepts
Database System Concepts
Computer Science
ISBN:
9780078022159
Author:
Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Publisher:
McGraw-Hill Education
Starting Out with Python (4th Edition)
Starting Out with Python (4th Edition)
Computer Science
ISBN:
9780134444321
Author:
Tony Gaddis
Publisher:
PEARSON
Digital Fundamentals (11th Edition)
Digital Fundamentals (11th Edition)
Computer Science
ISBN:
9780132737968
Author:
Thomas L. Floyd
Publisher:
PEARSON
C How to Program (8th Edition)
C How to Program (8th Edition)
Computer Science
ISBN:
9780133976892
Author:
Paul J. Deitel, Harvey Deitel
Publisher:
PEARSON
Database Systems: Design, Implementation, & Manag…
Database Systems: Design, Implementation, & Manag…
Computer Science
ISBN:
9781337627900
Author:
Carlos Coronel, Steven Morris
Publisher:
Cengage Learning
Programmable Logic Controllers
Programmable Logic Controllers
Computer Science
ISBN:
9780073373843
Author:
Frank D. Petruzella
Publisher:
McGraw-Hill Education