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?
$\begingroup$
$\endgroup$
2
-
$\begingroup$ What do you mean by "Is a Conv2DTranspose the same as a full convolution?"? Same in terms of what? $\endgroup$– nbroCommented Nov 8, 2021 at 13:01
-
$\begingroup$ Yes I mean are they referring to the same opperation. $\endgroup$– Sean MabliCommented Nov 9, 2021 at 22:37
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
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