10 Years of Celebrating Indie Authors

Share this book with your friends

CNN KERNEL Performance analysis based on kernel size of Convolutional Layers in a network

Author Name: Al Mahmud Al Mamun | Format: Paperback | Genre : Educational & Professional | Other Details

In this book, I perform an experimental review on twelve similar types of Convolutional Neural Network architecture but the different sizes of kernels for the filters. 

For this experiment, I select twelve different sizes of the kernel for twelve Convolutional Neural Network models, the size of kernels are – (12, 12), (11, 11), (10, 10), (9, 9), (8, 8), (7, 7), (6, 6), (5, 5), (4, 4), (3, 3), (2, 2), and (1, 1). 

For this experiment, I use the “Flowers Recognition” dataset. I use 77 batches (batch size = 45) per epoch and 10 epochs per experimental fold.

After analyzing the results, I found that according to the performance, kernel_size (2, 2) and (3, 3) are the best selection for the two-dimensional convolutional layer in the convolutional neural networks.

The goal of this experiment is to help the developer to understand and select the perfect size of the kernel for filter during two-dimensional image processing by using the two-dimensional Convolutional (Conv2D) layer [11] of CNNs.

Paperback 300

Inclusive of all taxes


Item is available at

Enter pincode for exact delivery dates

Also Available On

Al Mahmud Al Mamun

He earned his Bachelor of Science in Computer Science and Engineering from Prime University, Bangladesh. His Masters of Science in Computer Science and Engineering is in progress from Islamic University, Bangladesh. He attained twenty-seven diploma courses and a hundred certificate courses.

His expertise and research interests include Artificial Intelligence, Artificial Neural Networks, Convolutional Neural Networks, Intelligent Transportation Systems, Information Technology, System Development Life Cycle, Computer Vision, Psychology, and Astronomy.

In 2009, he joined as a Managing Director at Kushtia Diabetic and Medical Center, Bangladesh. He joined as a Lecturer in the Department of Computer Science and Engineering at Rabindra Maitree University in 2019. In 2021, he worked as Quality Assurance Engineer at GuideMe Solutions, Australia. In the same year, he joined as a writer at Technology Advice, United States.