cioscos / gpen-cioscos Goto Github PK
View Code? Open in Web Editor NEWPersonal GPEN scripts within the GPEN-Windows stand-alone package.
Personal GPEN scripts within the GPEN-Windows stand-alone package.
Hi,
I ran this software on my PC with a 2080ti and it worked great.
For some reason though, on the 3090-pc, it doesn't work for me.
When I run the aligned images script I get this error:
D:\Bureaublad\GPEN-Windows\_internal\CUDA\bin\nvcc --generate-dependencies-with-compile --dependency-output fused_bias_act_kernel.cuda.o.d -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -DTORCH_EXTENSION_NAME=fused -DTORCH_API_INCLUDE_EXTENSION_H -ID:\Bureaublad\GPEN-Windows\_internal\Python37\lib\site-packages\torch\include -ID:\Bureaublad\GPEN-Windows\_internal\Python37\lib\site-packages\torch\include\torch\csrc\api\include -ID:\Bureaublad\GPEN-Windows\_internal\Python37\lib\site-packages\torch\include\TH -ID:\Bureaublad\GPEN-Windows\_internal\Python37\lib\site-packages\torch\include\THC -ID:\Bureaublad\GPEN-Windows\_internal\CUDA\include -ID:\Bureaublad\GPEN-Windows\_internal\Python37\Include -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 -c D:\Bureaublad\GPEN-Windows\face_model\op\fused_bias_act_kernel.cu -o fused_bias_act_kernel.cuda.o nvcc fatal : Could not set up the environment for Microsoft Visual Studio using 'D:/Bureaublad/GPEN-Windows/_internal/Microsoft Visual Studio/2019/Community/VC/Tools/MSVC/14.29.30133/bin/HostX86/x64/../../../../../../../VC/Auxiliary/Build/vcvars64.bat' ninja: build stopped: subcommand failed.
What could fix this?
Also, thanks for creating the GPEN-windows scripts!
It would interesting to have some scripts to integrate SwinIR in the GPEN batch scripts. So far it seems to be the best for super-resolution at the moment.
https://github.com/JingyunLiang/SwinIR
Pensi si possa integrare?
Marco.
Hello Pioneer Technologist:
I'm very happy to share it, it's very good!
Can you provide training methods, such as how to set in batch processing files.
I only have one GPU 1070, I don’t know if it can be executed.
Sorry to bother you, if you have time to trouble please take the time to reply, thank you again!
" %PYTHON_EXECUTABLE% " train_simple.py --size 256 --channel_multiplier 1 --narrow 0.5 --ckpt .\training_weight\010000.pth --sample .\results\sample --batch 1 --path input\training-data
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.