论文代码配环境—Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers .

type

status

date

slug

summary

category

icon

password

🔧

使用autodl rtx2080ti

选择torch1.5.0+cuda10.1

代码：

blackbox-deep-graph-matching

martius-lab • Updated Mar 14, 2024

论文：

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified...

https://arxiv.org/abs/2003.11657

requirments

Pillow (<7):

Scipy (1.4.1):

EasyDict (1.9):

这个包可能不直接在Conda的仓库中

Torch (1.4.0):

自带1.5.0先不装这个

注意，我同时为torchvision提供了安装命令，因为它们通常一起安装，并且指定了适合这个版本的torchvision版本。

lpmp_py:

LPMP

LPMP • Updated May 20, 2024

官方步骤：

Type git clone https://github.com/LPMP/LPMP.git for downloading, then cd LPMP and git submodule update --init --remote --recursive for downloading dependencies and finally cmake . for building.

Prerequisites:

Clang 5.0 or GCC 8.0 upwards for C++17 compatibility (see here for installation instructions).

HDF5 (install with apt install libhdf5-serial-dev)

cmake (install with apt install cmake)

我的步骤：

PyTorch Geometric 相关包 (torch-geometric, torch-sparse, torch-scatter, torch-cluster, torch-spline-conv):

版本是参考另一个项目的版本torch1.4.0

这里每一个包安装都很慢，大概要十分钟，原因未知

遇到报错：

ModuleNotFoundError: No module named 'torch.profiler' - 知乎 (zhihu.com)

顺利解决

🗒️论文代码配环境—Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers .

requirments