diningphil / graph-mixture-density-networks Goto Github PK
View Code? Open in Web Editor NEWOfficial Repository of "Graph Mixture Density Networks" (ICML 2021)
License: BSD 3-Clause "New" or "Revised" License
Official Repository of "Graph Mixture Density Networks" (ICML 2021)
License: BSD 3-Clause "New" or "Revised" License
Hi,
I'm completely new to this area so I just started with a code after installing the environment of python 3.7 for DGL4.0 and PYDGN==0.5.1. And I've runned the code "python build_dataset.py --config-file GMDN_DATA_CONFIG/config_alchemy_full.yml". However, I encountered the following problem.
EDIT: The command I used was: python launch_experiment.py --config-file GMDN_MODEL_CONFIG/PROTEINS/GMDN/config_GMDN_alchemy_full.yml --splits-folder GMDN_SPLITS/ --data-splits GMDN_SPLITS/alchemy_full/alchemy_full_outer1_inner1.splits --data-root DATA --dataset-name alchemy_full --dataset-class gmdn_dataset.TUDatasetInterface --max-cpus 1 --max-gpus 1 --final-training-runs 10 --result-folder RESULTS
This seemed to be a warning but not a direct termination, while the Out_1/Inn_1 ratio is always 0/72 and not making any progress so it makes me worried now. Is there anything else I need to do before this step? Thanks a lot!
**************************************** Experiment Progress ***************************************
Out_1/Inn_1: 0%| |0/72, (1 cfg every 0:00:00)(run_valid pid=33770) /home/xf/anaconda3/envs/testGMDN/lib/python3.7/site-packages/torch_geometric/deprecation.py:13: UserWarning: 'data.DataLoader' is deprecated, use 'loader.DataLoader' instead0:00:00)
(run_valid pid=33770) warnings.warn(out)
(run_valid pid=33770) E0227 14:42:12.118239815 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:12.152389978 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:12.187567724 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:12.214780459 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:22.587925394 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:22.647595318 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:22.707876652 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategies
(run_valid pid=33770) E0227 14:42:22.748048284 33770 fork_posix.cc:70] Fork support is only compatible with the epoll1 and poll polling strategi
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.