Stack Overflow
Stack Overflow

Questions tagged [stylegan]

45 questions
12
votes
3 answers

Tensorflow 1.14 performance issue on rtx 3090

I am running a model written with TensorFlow 1.x on 4x RTX 3090 and it is taking a long time to start up the training than as in 1x RTX 3090. Although, as training starts, it gets finished up earlier in 4x than in 1x. I am using CUDA 11.1 and…
Thunder
  • 459
  • 3
  • 14
3
votes
1 answer

numpy.core._exceptions.MemoryError: Unable to allocate 0 bytes for an array with shape (1073741824, 0) and data type float32

I'm trying to train StyleGAN2, but everytime I'm starting to train I'm getting this error. It's weird that it can't allocate 0 bytes. Log: Traceback (most recent call last): File "train.py", line 561, in main() File "train.py", line…
Denking
  • 31
  • 1
  • 4
3
votes
1 answer

How to make Python libraries accessible in PYTHONPATH?

I am trying to implement StyleGAN2-ADA PyTorch: https://github.com/NVlabs/stylegan2-ada-pytorch. On the GitHub repo, it states the following: The above code requires torch_utils and dnnlib to be accessible via PYTHONPATH. It does not need source…
Dino Anastasopoulos
  • 31
  • 3
3
votes
1 answer

RuntimeError: Ninja is required to load C++ extensions

I've downloaded an implementation of stylegan2 from the following github: I added the path to my PYTHONPATH variable and now when importing their models I get the following error: RuntimeError: Ninja is required to load C++ extensions I'm working…
crommy
  • 433
  • 1
  • 4
  • 12
3
votes
0 answers

stylegan2 - tensorflow.python.framework.errors_impl.InvalidArgumentError

I try to train with my custom dataset that shape 256x256 This is stylegan2 code : https://github.com/NVlabs/stylegan2.git I prepared dataset with this command : !mkdir dataset !tar -xf data.tar !python dataset_tool.py create_from_images_raw…
SEAN
  • 31
  • 2
3
votes
0 answers

How to interpolate between two pictures of the latent space using StyleGAN2

I'm trying to interpolate between two pictures of the latent space using this implementation of StyleGan2 : https://github.com/justinpinkney/stylegan2.git Here's how i'm projecting my 2 original pictures to the latent space. From there I would like…
mlvt
  • 31
  • 2
2
votes
1 answer

StyleGAN3 images become under- or overexposed with an evolving dataset

I am trying to use StyleGAN3 with an evolving dataset, my current logic is as follows: Train for about half an hour Regenerate dataset with added images Resume training with --resume For testing, I've been using the metfaces dataset and started…
Taavi
  • 21
  • 2
2
votes
1 answer

What do the numbers mean when you are training a NVlabs/stylegan2

What do these numbers mean when you are training a style-gan tick 60 kimg 242.0 time 1h 55m 54s sec/tick 104.7 sec/kimg 25.96 maintenance 0.0 gpumem 7.3 augment 0.105 The one that I'm worried about is Augment cause it appears to be…
Some Guy Trying To Do Math
  • 466
  • 3
  • 16
1
vote
1 answer

When trying to convert StyleGan2 Pickle File, getting pickle.load() error: 'No module named 'torch_utils.persistence'

I trained a StyleGan2-ADA model on a custom dataset which generated a .pkl file. I'm now trying to load the .pkl file so that I can convert it to a .pt file, but when I load the .pkl file using: pickle.load(f) I'm getting a ModuleNotFoundError: No…
Naveen M
  • 11
  • 1
1
vote
0 answers

Model Training Freezing StyleGAN2 in Google CoLab

I want to train a model using this dataset : https://decode.mit.edu/projects/biked/ and I followed this tutorial to do such : https://github.com/jeffheaton/present/blob/master/youtube/gan/colab_gan_train.ipynb The Problem is once I start the command…
ii_7sn001
  • 45
  • 4
1
vote
0 answers

StyleGan3. The program hangs on Setting up PyTorch plugin “filtered_lrelu_plugin”

I use StyleGan3 from this repository GitHub - NVlabs/stylegan3: Official PyTorch implementation of StyleGAN3. I had everything working fine, but at some point, I interrupted the program without letting it finish. And now I’m facing the fact that the…
Игорь Платонов
  • 11
  • 3
1
vote
3 answers

ImportError: cannot import name 'notf' from 'tensorboard.compat'

i am training stylegan2-ada-pytorch from google colab with my custom images however on trying to perform the initial training i get the above error from tensorboard cmd = f"/usr/bin/python3 /content/stylegan2-ada-pytorch/train.py --snap {SNAP}…
Blaq_2022
  • 13
  • 1
  • 6
1
vote
0 answers

Problem with training stylegan3 - got stuck on Setting up PyTorch plugin "upfirdn2d_plugin"

I faced a problem on training stylegan3 where the terminal stuck at "Setting up PyTorch plugin "upfirdn2d_plugin"... ". I have tried all the methods I found, such as reinstall conda, re-download the whole stylegan3 to retrain the whole network, and…
Fu Wenjin
  • 11
  • 2
1
vote
0 answers

training GAN_How to use Local gpu on Google Colab?

Hello ，I have a problem when I am using Google Colab. I tried to use my Local GPU on Colab,and I had been connected to Google Colab with my Jupyter, but when I tried to execute the instruction : !python train.py…
Clary
  • 11
  • 2
1
vote
1 answer

StyleGAN2 fails on missing Windows compiling environment of Visual Sutdio 2022

I am trying to run the stylegan2 project by calling the below command: python run_generator.py generate-images --network=gdrive:networks/stylegan2-ffhq-config-f.pkl --seeds=6600-6625 --truncation-psi=0.5. However, the program encounters an…
James
  • 1,373
  • 3
  • 13
  • 27
1
2 3