Skip to main content
Data Science

Return to Question

Typo
Source Link
Lau
Lau
  • 226
  • 2
  • 8

currentlyCurrently I read a paper about symmetric skip connections for autoencoder (link). One experiment of them changes the the 'training patch size'.

In my understanding patches are sub box-boxes of an image that is used at one time of an convolutional layer. So if you have a 3x3 filter the patch is a part of the image with the size 3x3.

Do they mean by 'training patch size' the size of the input image? (The network is a symmetric autoencoder, so the input size is arbitrary)

Thanks in advance

currently I read a paper about symmetric skip connections for autoencoder (link). One experiment of them changes the the 'training patch size'.

In my understanding patches are sub box of an image that is used at one time of an convolutional layer. So if you have a 3x3 filter the patch is a part of the image with the size 3x3.

Do they mean by 'training patch size' the size of the input image? (The network is a symmetric autoencoder, so the input size is arbitrary)

Thanks in advance

Currently I read a paper about symmetric skip connections for autoencoder (link). One experiment of them changes the the 'training patch size'.

In my understanding patches are sub-boxes of an image that is used at one time of an convolutional layer. So if you have a 3x3 filter the patch is a part of the image with the size 3x3.

Do they mean by 'training patch size' the size of the input image? (The network is a symmetric autoencoder, so the input size is arbitrary)

Thanks in advance

Source Link
Lau
Lau
  • 226
  • 2
  • 8

What is meant by 'training patch size'?

currently I read a paper about symmetric skip connections for autoencoder (link). One experiment of them changes the the 'training patch size'.

In my understanding patches are sub box of an image that is used at one time of an convolutional layer. So if you have a 3x3 filter the patch is a part of the image with the size 3x3.

Do they mean by 'training patch size' the size of the input image? (The network is a symmetric autoencoder, so the input size is arbitrary)

Thanks in advance