关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
zhanghongyi
/
pytorch_geometric
mirror of https://github.com/pyg-team/pytorch_geometric
Not watched
1
0
Fork 2
Code
Releases 40 Wiki Activity
Issues 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
7515 Commits
110 Branches
848 MiB
1041 Download
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
pytorch_geometric/benchmark
Matthias Fey 12f6dcb786
Drop `import torch.mps` in benchmark (#9053) 		1 month ago
..
citation Drop `import torch.mps` in benchmark (#9053) 1 month ago
inference Make `MessagePassing` interface thread-safe (#9001) 2 months ago
kernel Drop `import torch.mps` in benchmark (#9053) 1 month ago
loader Adds support for benchmarking bidirectional sampling (#7415) 11 months ago
multi_gpu/training Use `find_unused_parameters` only for heterogeneous cases (#8592) 4 months ago
points Drop `import torch.mps` in benchmark (#9053) 1 month ago
runtime Drop `import torch.mps` in benchmark (#9053) 1 month ago
training Add `mdformat` as a markdown formatter (#8462) 5 months ago
utils Fix errors in benchmarks (#7956) 8 months ago
README.md Rename (#3119) 2 years ago
setup.py sort imports via isort 2 years ago

README.md

PyG Benchmark Suite

This benchmark suite provides evaluation scripts for semi-supervised node classification, graph classification, and point cloud classification and runtimes in order to compare various methods in homogeneous evaluation scenarios.
In particular, we take care to avoid to perform hyperparameter and model selection on the test set and instead use an additional validation set.

Installation

$ pip install -e .
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

Python CSV HTML+Django Shell other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit