CODEWITHSUNDEEP
tensorflowdeep-learningconv-neural-network
배준호
배준호

Reputation: 139

What's difference between Summation and Concatenation at neural network like CNN?

What's difference between summation and concatenation at neural network like CNNs?

For example Googlenet's Inception module used concatenation, Resnet's Residual learning used summation.

Please teach me.

Upvotes: 2

Views: 3158

Answers (1)

rkellerm
rkellerm

Reputation: 5522

Concatenation means to concatenate two blobs, so after the concat we have a bigger blob that contains the previous blobs in a continuous memory. For example:
blob1:

1
2
3

blob2:

4
5
6

blob_res:

1
2
3
4
5
6

Summation means element-wise summation, blob1 and blob2 must have the exact same shape, and the resultant blob has the same shape with the elements a1+b1, a2+b2, ai+bi, ... an+bn. For the example above,
blob_res:

(1+4) 5
(2+5) 7
(3+6) 9

Upvotes: 2

Related Questions