{"id":17403748,"url":"https://github.com/link89/dflow-samples","last_synced_at":"2025-03-27T22:34:18.601Z","repository":{"id":81055155,"uuid":"567550475","full_name":"link89/dflow-samples","owner":"link89","description":"evaluate dflow from deepmodeling","archived":false,"fork":false,"pushed_at":"2022-11-30T01:57:21.000Z","size":133,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-02T00:47:51.557Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/link89.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-11-18T02:52:28.000Z","updated_at":"2023-09-18T08:22:23.000Z","dependencies_parsed_at":"2023-03-25T13:33:29.898Z","dependency_job_id":null,"html_url":"https://github.com/link89/dflow-samples","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/link89%2Fdflow-samples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/link89%2Fdflow-samples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/link89%2Fdflow-samples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/link89%2Fdflow-samples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/link89","download_url":"https://codeload.github.com/link89/dflow-samples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245937280,"owners_count":20696974,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-16T19:07:50.967Z","updated_at":"2025-03-27T22:34:18.552Z","avatar_url":"https://github.com/link89.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# dflow-samples\n\n基于 dflow 和 Bohrium 的工作流项目示例。\n\n## 使用\n\n### 在本地执行\n\n使用前需安装依赖如下：\n\n```bash\npoetry install\npip install tensorflow==2.10.1  # 如已通过conda或其它途径安装可省略此步\n```\n\n然后即可通过以下命令调用实现的方法 (其中训练所用的 outcar 文件和预测所用的轨迹文件均为预先生成)\n\n```bash\npython -m dflow_samples.main train_model --elements=[Na] --outcar_folders=\"['./data/nmr/p6322', './nmr/data/train/p63mcm']\"\n\npython -m dflow_samples.main predict --elements=[Na] --traj_path=./data/nmr/predict_fcshifts_example.xyz --model=./out/model \n```\n\n### 通过 Docker 执行\n\n为支持在 dflow 执行，该项目提供了Dockerfile用于构建用于代码执行的容器，使用前先使用以下命令确保容器被正确构建\n\n```bash\ndocker build -t dflow-nmr .\n```\n\n构建完成后可通过以下命令执行（注意需要将外部数据目录挂载到内部, 输出模型也需指定到挂载目录上）\n\n```bash\n docker run -v $PWD/data/nmr:/data dflow-nmr python -m dflow_samples.main train_model --elements=[Na] --outcar_folders=\"['/data/train/p6322', '/data/train/p63mcm']\" --out_dir /data/out\n\n docker run -v $PWD/data/nmr:/data dflow-nmr python -m dflow_samples.main predict --elements=[Na] --traj_path=/data/predict_fcshifts_example.xyz --model=/data/out/model\n```\n\n### 通过 Singularity 执行\n\n为支持在 Bohrium 平台运行，首先需要将 docker 镜像转换为 singularity 镜像并上传到嘉庚超算的容器目录中。\n\n在本地构建镜像可以使用 conda 安装 singularity的运行时:\n\n```bash\nconda install -c conda-forge singularity\n```\n\nsingularity镜像可直接从 docker 镜像中转化\n\n```bash\nsingularity build dflow_nmr.sif docker-daemon://dflow-nmr:latest\n```\n\n构建完成后可使用以下命令执行\n\n```bash\nsingularity exec --bind ./data/nmr:/data dflow_nmr.sif python -m dflow_samples.main train_model --elements=[Na] --outcar_folders=\"['/data/train/p6322', '/data/train/p63mcm']\" --out_dir /data/out\n\nsingularity exec --bind ./data/nmr:/data dflow_nmr.sif python -m dflow_samples.main predict --elements=[Na] --traj_path=/data/predict_fcshifts_example.xyz --model=/data/out/model\n```\n\n### 在 Bohrium 平台上执行\n\n为了能够在 Bohrium 平台上使用嘉庚超算执行相关代码，需要将上一步生成的 sif 镜像部署到超算上的指定位置。\n\n部署完成后可参考此 [教程](./docs/tutorial.md) 去使用。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flink89%2Fdflow-samples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flink89%2Fdflow-samples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flink89%2Fdflow-samples/lists"}