Valid Padding in Convolution Neural Networks

@syed.danish wrote:

Hi all,
I was going through the valid padding technique in convolution neural nets on udacity deep learning course, where I came across a quiz in which we have a 28*28 image on which we ran 3*3 convolution with input depth of 3 and output depth of 8. We have to write the output dimension. I have attached a screenshot below with the solution.

Image may be NSFW.
Clik here to view.

Screenshot from 2016-07-20 20-34-22.png856x434 142 KB

I am unable to understand output dimension of the valid padding with 1 stride, why the output dimension turned out to be 26*26? Please help me with that.
Thanks in advance,
Syed Danish

Posts: 1

Participants: 1

Read full topic