0
$\begingroup$

I am currently creating a GAN model from scratch (following this tutorial: https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-an-mnist-handwritten-digits-from-scratch-in-keras/) but I can't find out how to implement Conv2DTranspose from scratch. Is a Conv2DTranspose the same as a full convolution? If not, how would one implement it?

$\endgroup$
2
  • $\begingroup$ What do you mean by "Is a Conv2DTranspose the same as a full convolution?"? Same in terms of what? $\endgroup$
    – nbro
    Commented Nov 8, 2021 at 13:01
  • $\begingroup$ Yes I mean are they referring to the same opperation. $\endgroup$
    – Sean Mabli
    Commented Nov 9, 2021 at 22:37

1 Answer 1

1
$\begingroup$

Con2DTranspose is an upsampling method used to increase the size of an image.

When we perform convolution, the size of the image decreases, but in some scenarios, we want our image size to be the same as the input image size. Hence we use this convolution.

Here you will find Keras implementation on Conv2DTranspose

https://github.com/keras-team/keras/blob/v2.7.0/keras/layers/convolutional.py#L1093-L1394

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .