Super_res_net does it include generator and discriminator or only generator

Physics Simulation PhysicsNeMo-ML Model Framework Technical Support (PhysicsNeMo Only)
1

Dear all,

In the documentation of the super_res_net, it is written that the code is based on the implementation of this github page (GitHub - sgrvinod/a-PyTorch-Tutorial-to-Super-Resolution: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution).
This github page has two architectures SRResNet and SRGAN.
The SRResNet has only generator and the SRGAN has generator and discriminator.

I am not sure of the super_res_net in Nvidia Modulus included the discriminator as well in the architecture or not.

Thanks in advance

2

Hi @omarkhaledsallam

SRResNet inside of modulus is just the generator (convolutional decoder) architecture designed to bring a low resolution image to a higher-fidelity one. Some documentation on it can be found here and an example that can use it can be found here.

3

Thanks for your reply,

Does the Pix2Pix include both generator and discriminator?

Thanks

4

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.