Questions tagged [stylegan]
45 questions
1
vote
0 answers
Why torch.device('cuda', 0) is not working and torch.cuda.device(0) is it?
first of all sorry about my english, I am going to try my best.
I am working with Stylegan3 and I get this error in this line
torch.device('cuda', 0)
Found GPU%d %s which is of cuda capability %d.%d.
PyTorch no longer supports this GPU because it…
Laura Alvarez
- 21
- 4
1
vote
0 answers
Running StyleGAN 2 on CPU
Is it possible to run the TensorFlow version of stylegan2 on the CPU? If, then what are the changes need to be made for it?
Thunder
- 459
- 3
- 14
1
vote
1 answer
FastGAN - RuntimeError: Error(s) in loading state_dict for Generator
I'm running FastGAN (https://github.com/odegeasslbc/FastGAN-pytorch) on Google Colab and now trying to resume training from a saved .pth generated by the network. However, it keeps throwing this error:
Traceback (most recent call last):
File…
KT9000
- 35
- 6
1
vote
4 answers
trying to run styleGAN in jyputer notebook, it says "tensorflow' has no attribute 'Dimension"
enter image description here!python encode_images.py --optimizer=lbfgs --face_mask=True --iterations=6 --use_lpips_loss=0 --use_discriminator_loss=0 --output_video=True aligned_images/ generated_images/ latent_representations/
print("\n************…
Vijay Mishra
- 11
- 1
- 2
1
vote
2 answers
Stylegan2-ada tfrecords - ValueError: axes don't match array, images will work one run and not work the next
I'm working on training a GAN through Google Colab with a dataset of photos I scraped from Wikiart and converted to 1024x1024, but keep getting this error when creating the tfrecords:
Traceback (most recent call last):
File "dataset_tool.py", line…
richvar
- 31
- 5
1
vote
1 answer
StyleGAN2-ada, Runtime runs, but epoch stays at zero
I run it on the Colab
runtime runs.... But even if I wait for more than 5 hours, epoch doesn't go up. Is there any problem should I check??
!nvidia-smi
> NVIDIA-SMI 455.32.00
Driver Version: 418.67
CUDA Version: 10.1
Tesla V100-SXM2...
24W / 300W…
seongbeom shin
- 23
- 5
1
vote
0 answers
OutOfRangeError while training StyleGan2 network
I've been running into plenty of problems training my first network using the StyleGAN2 repo and after changing to a smaller GPU batch size of 2 because of only 11GB of VRAM available to me the training manages to get through 1-4 ticks before…
shaun_lodestar
- 11
- 1
1
vote
1 answer
WHat does Lambda do in this code (python keras)?
def AdaIN(x):
#Normalize x[0] (image representation)
mean = K.mean(x[0], axis = [1, 2], keepdims = True)
std = K.std(x[0], axis = [1, 2], keepdims = True) + 1e-7
y = (x[0] - mean) / std
#Reshape scale and bias parameters
…
Rhodel Quizon
- 13
- 2
1
vote
0 answers
“ValueError: too many values to unpack (expected 3)” when trying to run StyleGAN2 generating command
Got this error when trying to use Derrick Schultz's repository for StyleGAN2 neural training in Google Colab https://github.com/dvschultz/ai/blob/master/StyleGAN2_Colab_Train.ipynb
The command were:
!python run_generator.py generate-images…
Xie Baoshi
- 11
- 2
1
vote
1 answer
StyleGAN2 get values of constant layer returning incompatible device assigned GPU vs CPU in Colab
I am trying to get values of StyleGAN generator constant layer using the following code in Google Colab with GPU runtime
v1 = (tflib.run(['G_synthesis_1/4x4/Const/const:0'])[0])
But I am getting the following error:
> InvalidArgumentError: Cannot…
javaCity
- 4,288
- 2
- 25
- 37
0
votes
0 answers
Troubleshooting StyleGAN3: training model collapse and warnings encountered during evaluation despite using --workers=2 flag
I am attempting to train StyleGAN3 on Google Cloud using the following setup:
2vCPU
13GB of RAM
Nvidia T4
PyTorch 1.13
CUDA 11.3
Python 3.10
My dataset consists of approximately 14,000 JPG images of dresses sketchs, which I converted to PNG format…
Casaw
- 1
- 1
0
votes
0 answers
StyleGAN2-ADA-PyTorch Training Stopped Unexpectedly without Error Messages
I was initially starting to train with google colab free. WHile I started another training and upgraded to colab pro for better efficiency. I was offered the a100 GPU and I simply ran the old code and tried to get the training started. Then it shows…
Bryan Y
- 9
- 1
0
votes
0 answers
stylegan not able to converge
I've built the stylegan and its training loop using Tensorflow from its research paper, I'm using celebA-HQ dataset of 30k images. But even after running more than 5000+ steps it is not showing any improvements. Can anyone help me in my script where…
Janvi Chokshi
- 11
- 2
0
votes
0 answers
How to build the bias_act_plugin extension for stylegan3
I am trying to run the code in stylegan3, and I am getting the error
RuntimeError: Error building extension 'bias_act_plugin'
I looked online for some ideas and they told me to install ninja with pip. I have done that I am still getting the error.…
odbhut.shei.chhele
- 5,834
- 16
- 69
- 109
0
votes
0 answers
I am training a custom dataset using StyleGAN 2 ADA with 2,832 images in Google Colab and my augment values are decreasing. Is this expected?
Training Results
If anyone can explain to me what is happening here, that would be most helpful.
I initially tried training with a dataset of 70 images and the augment values would increase, not go back to 0.0. I am expecting that my augment values…
r2b2
- 9
- 2