Shashika Chamod
Mar 31, 2021

The shape of the kernel (Ex 3x3 vs 7x7) directly affects the hyper-parameters we selected for training. If you select larger kernel first, you intend to capture larger spatial features first hence the depth of the network (number of layers) is reduced, but remember it has a cost of losing small important features at the very beginning.

Sign up to discover human stories that deepen your understanding of the world.

Free

Distraction-free reading. No ads.

Organize your knowledge with lists and highlights.

Tell your story. Find your audience.

Membership

Read member-only stories

Support writers you read most

Earn money for your writing

Listen to audio narrations

Read offline with the Medium app

Shashika Chamod
Shashika Chamod

Written by Shashika Chamod

Biomedical Engineer (R&D), AI Enthusiast

Responses (1)

Write a response