Comments (8)
Hi @dfaghani, thanks for your feedback. I strongly recommend running on a GPU machine since the computation would be heavy for CPUs. But anyway, I will be fixing this problem and make it compatible with a CPU machine tonight. I will let you know when it's ready to use.
from stylized-neural-painting.
Hi @dfaghani, PyTorch-CPU mode is now supported! You can try out on your local machine without any GPU cards. But please note that you still need PyTorch installed if you run on CPU mode. You can simply follow the instructions in the README file and the code will automatically detect whether there will be any GPU cards available. If there is no GPU, the code will run on the CPU automatically. Please let me know if there is any problem. Thanks!
from stylized-neural-painting.
Hwllo,
Thank you for your quick response.
I am still getting error messages.
Will try to sort it out but might revert for more help!
Thank you again,
Best,
DF
from stylized-neural-painting.
Hi @dfaghani, maybe you can post your error code here if you like. Me and other people are willing to help you.
from stylized-neural-painting.
Thank you for your support!
Here is the error message.
Upfront thanks.
DF
(base) Y:\8000-Publique\DF_Publique\PYTHON\stylized-neural-painting>python demo_prog.py --img_path ./test_images/apple.jpg --canvas_color 'white' --max_m_strokes 500 --max_divide 5 --renderer oilpaintbrush --renderer_checkpoint_dir checkpoints_G_oilpaintbrush --net_G zou-fusion-net
C:\ProgramData\Anaconda3\lib\site-packages\torch\cuda_init_.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:100.)
return torch._C._cuda_getDeviceCount() > 0
initialize network with normal
pre-trained renderer does not exist...
from stylized-neural-painting.
Hi @dfaghani, it seems your pre-trained renderer can't be found. Have you downloaded those pre-trained models from Google Drive and unzip them to your repo folder?
from stylized-neural-painting.
Hi,
You are absolutely right!
When I pulled the cpu version, I forgot to copy the renderers.
Many thanks!
It is running.
Eager to see the result :-)
Kind regards and keep going!
Best,
DF
from stylized-neural-painting.
@dfaghani haha, that happens! Congratulations!
from stylized-neural-painting.
Related Issues (20)
- Advice on combining CLIP with the neural renderer HOT 3
- MacBook HOT 4
- intersection brushstroke question HOT 7
- brush_alpha erro HOT 2
- Google drive not letting me download the oil pretrained HOT 1
- Style Transfer Colab Notebook error HOT 2
- 文件版许可证与readme中的内容不符 HOT 1
- Rendering Vector To Image
- About training new painting styles HOT 1
- style transfer in demo_nst.py
- ImportError: cannot import name 'is_url' from 'runway.utils'
- Graphics card not working
- The difference of _render and _drawing_step_states
- Cannot find zipfile directory HOT 2
- Limiting brush stroke sizes
- 2 Questions about the method of this paper
- Ask some questions about this project
- How can change the color and shape parameter of the input picture?
- 詢問資料集相關事宜
- What Exactly AI do?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stylized-neural-painting.