training with different input size

[SaharR1372]

Hello,
Thanks for your spectacular paper and materials.
I want to train your network when my input size is 16x16 or 32x32 and output is 256x256.
I think I can not use your provided pretarined weight (ffhqx16) for finetunig, 1- is it true? because you used styleGAN specific to 1024.

So, I should use the special stylegan which is for 256. I have download it from:
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/stylegan2/files
; but I can not find the discriminator pretrain weight. 2-would u please help me to find it?

and as I checked the file (glean_ffhq_16x.py and below screenshot), I should change input size=16, output size=256, style channels=256, and ckpt_path of generator and discrimator URL. 3- are these true? is there anything else that I should change?

Thanks in advance.

[ckkelvinchan]

You can find the 256 StyleGAN in MMGeneration.

[SaharR1372]

Thank you for your reply.
According to what you mentioned, I have placed this model: stylegan2_c2_ffhq_256_b4x8_20210407_160709-7890ae1f.pth
But I got errors like below:

Would you please help me to how fix it?

[ckkelvinchan]

The error log said that you loaded the wrong model. The weights in the defined model and checkpoint do not match