Transpose convolution

1. What is a transpose convolution?
2. How do you calculate transpose convolution?
3. Is transposed convolution same as deconvolution?
4. What are the two names transpose convolution?

What is a transpose convolution?

Transposed convolutions are standard convolutions but with a modified input feature map. The stride and padding do not correspond to the number of zeros added around the image and the amount of shift in the kernel when sliding it across the input, as they would in a standard convolution operation.

How do you calculate transpose convolution?

Again, assuming square shaped tensors, the formula for transposed convolution is: Let's try this with Example 7, where the input size = 3, stride = 2, padding = 1, kernel size = 2. The calculation is then simply 2*2 - 2 + 1 + 1 = 4, so the output is of size 4.

Is transposed convolution same as deconvolution?

A transposed convolutional layer attempts to reconstruct the spatial dimensions of the convolutional layer and reverses the downsampling and upsampling techniques applied to it. A deconvolution is a mathematical operation that reverses the process of a convolutional layer.

What are the two names transpose convolution?

Stride over the output is equivalent to a 'fractional stride' over the input, and this is where the alternative name for transposed convolutions called 'fractionally strided convolutions' comes from. A stride of 2 over the output would be equivalent to a stride of 1/2 over the input: a fractional stride.