Stack Overflow
Stack Overflow

Questions tagged [stylegan]

45 questions
0
votes
0 answers

I am conducting transfer learning of StyleGan3 to another custom dataset

Trying to transfer learning to another custom datset using stylegan3. I reached this mentioned error due to the size of images. How can i go through this problem and furnish the appropriate size of dataset image 1024*1024. File…
Walid Messaoud
  • 1
0
votes
1 answer

ModuleNotFoundError: No module named '__builtin__' Stylegan XL

I'm running a modified version of stylegan 3 with the provided conda env on popOS 22.04 that can be found here: https://github.com/autonomousvision/stylegan_xl When training finishes or resumes I get the following error. I think it has to do with…
Nicholas
  • 1
0
votes
0 answers

STYLEGAN ADA2 implemenation on melanoma dataset

I went through your article titled "Training StyleGAN2 ADA with a custom dataset" and try to reproduce it on my own dataset of melanoma skin cancer. I resized all the images to 1024*1024 and followed all the steps you mentioned in your…
user1726297
  • 1
0
votes
1 answer

how to disable metrics calculation in styleGAN2?

Metrics calculation is very time consuming in stylegan2 is there any way to disable this feature. I want to train my network on Colab an this takes a lot of time
Nima Aghayan
  • 109
  • 1
  • 7
0
votes
2 answers

How does Mapping Network in StyleGAN work?

I am learning StyleGAN architecture and I got confused about the purpose of the Mapping Network. In the original paper it says: Our mapping network consists of 8 fully-connected layers, and the dimensionality of all input and output activations—…
Fedoruka
  • 61
  • 5
0
votes
1 answer

Using custom StyleGAN2-ada network in GANSpace (.pkl to .pt conversion)

I trained a network using Nvdia's StyleGAN2-ada pytorch implementation. I now have a .pkl file. I would like to use the GANSpace code on my network. However, to use GANSpace with a custom model, you need to be able to give it a checkpoint to your…
Claire
  • 1
  • 1
0
votes
1 answer

Generate images from a grayscale trained GAN pkl file

I have trained a stylegan using a set of grayscale images, now I am stuck in the generate.py because it is all set for generating RGB images. I get this error: ValueError: not enough image data when I changed the generate.py archive from stylegan…
velamini
  • 1
0
votes
1 answer

Stylegan3: How to save specific tick state in a file and resume training from that file?

I'm using Google Colab to train Stylegan3 on my data. I can resume from .pkl file. But I want to save a specific tick state in a file and then resume training from that file. How can I do it? I've checked PyTorch model saving and resuming but no…
InsParbo
  • 390
  • 2
  • 13
0
votes
1 answer

StyleGan2 ADA PyTorch Output Image Resolution Assertion Error

I am trying to produce an image using StyleGan2. Executing this cell: !python train.py --gpus=1 --cfg=$config --metrics=None --outdir=./results --data=$dataset_path --snap=$snapshot_count --resume=$resume_from --augpipe=$augs…
merkwur
  • 51
  • 5
0
votes
1 answer

how to make stylegan using tensorflow pretrained models in android

How to use python pretrained models in android . I want to make similar cartoon effect project in android . What are the steps to get similar Cartoonify effects in android. Mostly projects are using python. Below are the links referring to the…
Ayushi Jain
  • 1
  • 1
0
votes
1 answer

Unrecognized arguments using generate.py StyleGAN 2 ADA

I have trained the ffqh1024 model of StyleGAN 2 ADA (link to their repo) with a custom mammograms dataset in Google Colab. My trained model .pkl file is ready on a drive folder and I want to generate images using that .pkl file. I tried: !python…
user15468984
0
votes
1 answer

dimensions must equal error but they are equal

I added a print to the "discriminator_loss" function to see what was going on. at first it will tell me the shape of both are 16. later it tells me the shape of "real_loss" is only 15 while the other stays 16. So far I have only tried lowering the…
Will Mulcahey
  • 89
  • 1
  • 7
0
votes
1 answer

StyleGAN2 "Your session crashed after using all available RAM" at the start of training in Google Colab

Google Colab crashes when I starting to train my StyleGAN2 model, after tick 0. The error "Your session crashed after using all available RAM" appears. I'm using a fork of StyleGAN2 where added supporting of non-square images. Dataset consists of…
Xie Baoshi
  • 11
  • 2
-1
votes
1 answer

i have facing this error Input 0 is incompatible with layer model_14: expected shape=(None, 224, 224, 3), found shape=(1, 256, 256, 3)

this is the code i have tried but it gives me Input 0 is incompatible with layer model_21: expected shape=(None, 224, 224, 3), found shape=(1, 256, 256, 3) def loss_object(style_outputs, content_outputs, style_target, content_target): …
Dipanjal Rakshit
  • 1
  • 1
-1
votes
1 answer

Artifacts in StyleGAN generated images

I've written my own implementation of StyleGAN (paper here https://arxiv.org/abs/1812.04948), using PyTorch instead of Tensorflow, which is what the official implementation uses. I'm doing this partly as an exercise in implementing a scientific…
Kristoffer Sjöö
  • 286
  • 1
  • 9
1 2
3