-
Notifications
You must be signed in to change notification settings - Fork 9
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Solved problems on newer versions of pytorch, for Windows #25
base: master
Are you sure you want to change the base?
Conversation
There are some issues running this program on pytorch version>1.0 and is only on Linux/Unix but not on windows. See: https://discuss.pytorch.org/t/not-using-multiprocessing-but-getting-cuda-error-re-forked-subprocess/54610 Solved it
Tested on Ubuntu 18.04 LTS, with pytorch 1.7.1 and CUDA 11.0 on RTX 3090 |
@ValerieScarlet Thank you! I'll try this on my system and will merge if it yields same results as before. Might take a a few days but please know that your contribution is appreciated. |
Sorry it's taken me so long to try this out! Thanks again for your contribution. I'm confused, as the I see there's a new file called Could you clarify how to install this? Thanks. |
Error I get when using $ conda env create -f environment.yml
Collecting package metadata: done
Solving environment: failed
ResolvePackageNotFound:
- freetype==2.10.4=hd328e21_0
- numpy-base==1.19.2=py38ha3acd2a_0
- sip==4.19.13=py38ha925a31_0
- libpng==1.6.37=h2a8f88b_0
- libuv==1.40.0=he774522_0
- icu==58.2=ha925a31_3
- qt==5.9.7=vc14h73c81de_0
- libtiff==4.1.0=h56a325e_1
- mkl-service==2.3.0=py38h196d8e1_0
- pyqt==5.9.2=py38ha925a31_4
- vc==14.2=h21ff451_1
- zstd==1.4.5=h04227a9_0
- matplotlib-base==3.3.2=py38hba9282a_0
- pillow==8.1.0=py38h4fa10fc_0
- lz4-c==1.9.3=h2bbff1b_0
- xz==5.2.5=h62dcd97_0
- tornado==6.1=py38h2bbff1b_0
- openssl==1.1.1i=h2bbff1b_0
- mkl_random==1.1.1=py38h47e9c7a_0
- python==3.8.5=h5fd99cc_1
- mkl_fft==1.2.0=py38h45dec08_0
- numpy==1.19.2=py38hadc3359_0
- ca-certificates==2021.1.19=haa95532_0
- sqlite==3.33.0=h2a8f88b_0
- wincertstore==0.2=py38_0
- setuptools==52.0.0=py38haa95532_0
- vs2015_runtime==14.27.29016=h5e58377_2
- console_shortcut==0.1.1=4
- zlib==1.2.11=h62dcd97_4
- six==1.15.0=py38haa95532_0
- kiwisolver==1.3.0=py38hd77b12b_0
- ninja==1.10.2=py38h6d14046_0
- pytorch==1.7.1=py3.8_cuda110_cudnn8_0
- jpeg==9b=hb83a4c4_2
- matplotlib==3.3.2=haa95532_0
- tk==8.6.10=he774522_0
- cudatoolkit==11.0.221=h74a9793_0
- pip==20.3.3=py38haa95532_0
- certifi==2020.12.5=py38haa95532_0
|
|
Sorry for that. |
There are some issues running this program on pytorch version>1.0 and is only on Linux/Unix but not on windows. See: https://discuss.pytorch.org/t/not-using-multiprocessing-but-getting-cuda-error-re-forked-subprocess/54610
Solved it