CODEWITHSUNDEEP
neural-networkobject-recognitionpoolingdeep-learningsubsampling
Abhishek
Abhishek

Reputation: 3417

could not calculate the dimensions after pooling and subsampling in the famous Convolutional neural nets example

Hierarchical Models Of Perception and Reasoning by Yann LeCun

The above image is from a pdf by Yann LeCun, titled "Hierarchical Models Of Perception and Reasoning"

I am not able to understand the how the layer 2 is 14X14 feature maps? How can 75X75 matrix with 10X10 pooling and 5X5 subsampling gives 14X14 matrix ?

Upvotes: 1

Views: 3971

Answers (1)

deltheil
deltheil

Reputation: 16121

If you refer to this other paper by LeCun et al. an identical network is used with a larger input (143x143 grayscale image):

The first stage has 64 filters of size 9x9, followed by a subsampling layer with 5x5 stride, and 10x10 averaging window. [...]

This gives the right dimension:

output size = (input size - window size) / step + 1
            = (75-10) / 5 + 1
            = 14

Upvotes: 5

Related Questions