[go: up one dir, main page]
Scribd
Upload
62 views2 pages

Transposed Convolution

Transposed convolutional layers are used for upsampling in networks like auto-encoders and GANs, reversing the effects of downsampling in convolutional layers. They switch the input and output dimensions, resulting in a larger output, and can be affected by padding and strides. While often confused with deconvolution, transposed convolutions do not perfectly reverse convolution but instead reconstruct spatial dimensions without guaranteeing the same output as the input.

Uploaded by

mentorsahila
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
62 views2 pages

Transposed Convolution

Transposed convolutional layers are used for upsampling in networks like auto-encoders and GANs, reversing the effects of downsampling in convolutional layers. They switch the input and output dimensions, resulting in a larger output, and can be affected by padding and strides. While often confused with deconvolution, transposed convolutions do not perfectly reverse convolution but instead reconstruct spatial dimensions without guaranteeing the same output as the input.

Uploaded by

mentorsahila
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

3.

1 Transposed Convolution
The transposed convolutional layer, unlike the convolutional layer, is up sampling in nature. Transposed
convolutions are usually used in auto-encoders and GANs, or generally any network that must reconstruct an
image.
The word transpose means to cause two or more things to switch places with each other, and in the context of
convolutional neural networks, this causes the input and the output dimensions to switch.
In a transposed convolution, instead of the input being larger than the output, the output is larger. An easy way
to think of it is to picture the input being padded until the corner kernel can just barely reach the corner of the
input.

When down sampling and up sampling techniques are applied to transposed convolutional layers, their effects
are reversed. The reason for this is for a network to be able to use convolutional layers to compress the image,
then transposed convolutional layers with the exact same down sampling and up sampling techniques to
reconstruct the image.
When padding is ‘added’ to the transposed convolutional layer, it seems as if padding is removed from the
input, and the resulting output becomes smaller.
Without padding, the output is 7x7, but with padding on both sides, it is 5x5. When
strides are used, they instead affect the input, instead of the output.

Strides (2, 2) increases the output dimension from 3x3 to 5x5.


 Transposed Convolution vs Deconvolution
Deconvolution is a term floating around next to transposed convolutions, and the two are
often confused for each other. Many sources use the two interchangeably, and while
deconvolutions do exist, they are not very popular in the field of machine learning.
A deconvolution is a mathematical operation that reverses the effect of convolution.
Imagine throwing an input through a convolutional layer, and collecting the output. Now
throw the output through the deconvolutional layer, and you get back the exact same
input. It is the inverse of the multivariate convolutional function.
On the other hand, a transposed convolutional layer only reconstructs the spatial
dimensions of the input. In theory, this is fine in deep learning, as it can learn its own
parameters through gradient descent, however, it does not give the same output as the
input.

You might also like