【笔记】Bilevel代码

代码部分

环境配置

• 安装包

conda install pyyaml
export TORCH=1.12.1
export CUDA=cu116
pip install --no-index --upgrade torch-spline-conv==1.2.1 -f https://pytorch-geometric.com/whl/torch-${TORCH}+${CUDA}.html
pip install --no-index --upgrade torch-scatter==2.0.9 -f https://pytorch-geometric.com/whl/torch-${TORCH}+${CUDA}.html
pip install --no-index --upgrade torch-cluster==1.6.0 -f https://pytorch-geometric.com/whl/torch-${TORCH}+${CUDA}.html
pip install --no-index --upgrade torch-sparse==0.6.14 -f https://pytorch-geometric.com/whl/torch-${TORCH}+${CUDA}.html
pip install --upgrade torch-geometric==1.7.0
conda install -c anaconda texttable

• 查看版本的网址：https://pytorch-geometric.com/whl/torch-1.12.1%2Bcu116.html
• dataloader如果import报错，尝试下面的方法

# from torch._six import container_abcs, string_classes, int_classes
import collections.abc as container_abcs
int_classes = int
string_classes = str

• 错误：DiGraph object has no attribute nod

pip install networkx==1.11

• 错误：TypeError: ‘method’ object is not iterable
  忘记怎么解决的了
• vscode debug json配置

{
    // 使用 IntelliSense 了解相关属性。 
    // 悬停以查看现有属性的描述。
    // 欲了解更多信息，请访问: https://go.microsoft.com/fwlink/?linkid=830387
    "version": "0.2.0",
    "configurations": [
        {
            "name": "Python 调试程序: 当前文件",
            "type": "debugpy",
            "request": "launch",
            "program": "${file}",
            "console": "integratedTerminal",
            "env": {            
                "PATH": "${workspaceFolder}/.vscode/conda_env/bin",
                "CONDA_PREFIX": "${workspaceFolder}/.vscode/conda_env"            
            },            
            "args": ["--config", "ppo_bihyb_dag.yaml"],
        }
    ]
}

• 报错：If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
  去官网下载https://github.com/protocolbuffers/protobuf/releases

tar -xzf protobuf-all-3.19.0.tar.gz
cd protobuf-3.19.0
sudo apt-get update
sudo apt-get install -y build-essential cmake
./configure
make
sudo make install
sudo ldconfig -v
protoc --version
export PATH=$PATH:/usr/local/bin
source ~/.bashrc

结果没有解决，直接把tensorflow注释掉了

数据形式

dag_dict.py

Data Format: tpch_set, id = dag_data_dict[num_dags][tid][sample_id][dag_id]
维度：# (duration, resources)