Skip to main content
Cross Validated

Return to Question

Bumped by Community user
Bumped by Community user
Bumped by Community user
improved formatting, the bottom text was not readable before
Source Link
edit approved Feb 22, 2021 at 12:23
cwallenwein
edit approved Feb 22, 2021 at 12:23
cwallenwein
  • 113
  • 6

When understanding the inception module, I once saw the following statement from an online post. What's the calculation underline the "192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions"

Inception modules in convolutional networks were designed to allow for deeper and larger convolutional layers while at the same time allowing for more efficient computation. This is done by using 1×1 convolutions with small feature map size, for example, 192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions.

Inception modules in convolutional networks were designed to allow for deeper and larger convolutional layers while at the same time allowing for more efficient computation. This is done by using 1×1 convolutions with small feature map size, for example, 192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions.

When understanding inception module, I once saw the following statement from an online post. What's the calculation underline the "192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions"

Inception modules in convolutional networks were designed to allow for deeper and larger convolutional layers while at the same time allowing for more efficient computation. This is done by using 1×1 convolutions with small feature map size, for example, 192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions.

When understanding the inception module, I once saw the following statement from an online post. What's the calculation underline the "192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions"

Inception modules in convolutional networks were designed to allow for deeper and larger convolutional layers while at the same time allowing for more efficient computation. This is done by using 1×1 convolutions with small feature map size, for example, 192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions.

Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Source Link
user3269
user3269
  • 5.3k
  • 10
  • 48
  • 56

1x1 convolution for inception module

When understanding inception module, I once saw the following statement from an online post. What's the calculation underline the "192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions"

Inception modules in convolutional networks were designed to allow for deeper and larger convolutional layers while at the same time allowing for more efficient computation. This is done by using 1×1 convolutions with small feature map size, for example, 192 28×28 sized feature maps can be reduced to 64 28×28 feature maps through 64 1×1 convolutions.