From 0a010a14d9d95f09bd270c0713a6d36ae6c863bc Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Tue, 12 Nov 2024 11:53:39 +0800 Subject: [PATCH 01/10] science page --- docs/index.md | 229 ++------------------------ docs/javascripts/arxiv.js | 45 +++++ docs/zh/biology_medicine.md | 41 +++++ docs/zh/chemistry_material_science.md | 19 +++ docs/zh/competition.md | 9 + docs/zh/earth_science.md | 9 + docs/zh/fluid_mechanics.md | 82 +++++++++ docs/zh/get_link.py | 42 +++++ docs/zh/notebooks.md | 11 ++ docs/zh/overview.md | 123 -------------- docs/zh/pde.md | 27 +++ docs/zh/structral_mechanics.md | 3 + docs/zh/tutorials.md | 5 +- mkdocs.yml | 59 +------ 14 files changed, 307 insertions(+), 397 deletions(-) create mode 100644 docs/javascripts/arxiv.js create mode 100644 docs/zh/biology_medicine.md create mode 100644 docs/zh/chemistry_material_science.md create mode 100644 docs/zh/competition.md create mode 100644 docs/zh/earth_science.md create mode 100644 docs/zh/fluid_mechanics.md create mode 100644 docs/zh/get_link.py create mode 100644 docs/zh/notebooks.md delete mode 100644 docs/zh/overview.md create mode 100644 docs/zh/pde.md create mode 100644 docs/zh/structral_mechanics.md diff --git a/docs/index.md b/docs/index.md index edf114002..9a2258021 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,225 +1,16 @@ # PaddleScience - ---8<-- -./README.md:status ---8<-- - -🔥 [开放原子第二届开源大赛:飞桨科学计算工具组件开发大赛](https://competition.atomgit.com/competitionInfo?id=805ad94637707d062f24e54265d85731),总奖金25万人民币,火热报名中。 - -🔥 [PaddlePaddle Hackathon 7th 开源贡献个人挑战赛](https://github.com/PaddlePaddle/Paddle/issues/67603) - -🔥 [CIKM 2024: AI辅助的先进空气动力学-优化汽车设计以实现最佳性能](https://competition.atomgit.com/competitionInfo?id=cda4e961b0c25858ca0fd2a4bdf87520),已进入评奖阶段。 - -🔥 [IJCAI 2024: 任意三维几何外形车辆的风阻快速预测竞赛](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5),track A, B, C 代码:[paddle实现](https://github.com/PaddlePaddle/PaddleScience/tree/develop/jointContribution/IJCAI_2024) | [pytorch实现](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5)(点击**排行榜**可查看各个赛道前10名的代码) - - ---8<-- -./README.md:description ---8<-- - ---8<-- -./docs/zh/overview.md:panorama ---8<-- - -## 📝案例列表 - - -

数学(AI for Math)

- -| 问题类型 | 案例名称 | 优化算法 | 模型类型 | 训练方式 | 数据集 | 参考资料 | -|-----|---------|-----|---------|----|---------|---------| -| 亥姆霍兹方程 | [SPINN(Helmholtz3D)](./zh/examples/spinn.md) | 机理驱动 | SPINN | 无监督学习 | - | [Paper](https://arxiv.org/pdf/2306.15969) | -| 相场方程 | [Allen-Cahn](./zh/examples/allen_cahn.md) | 机理驱动 | MLP | 无监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/AllenCahn/allen_cahn.mat) | [Paper](https://arxiv.org/pdf/2402.00326) | -| 微分方程 | [拉普拉斯方程](./zh/examples/laplace2d.md) | 机理驱动 | MLP | 无监督学习 | - | - | -| 微分方程 | [伯格斯方程](./zh/examples/deephpms.md) | 机理驱动 | MLP | 无监督学习 | [Data](https://github.com/maziarraissi/DeepHPMs/tree/master/Data) | [Paper](https://arxiv.org/pdf/1801.06637.pdf) | -| 微分方程 | [非线性偏微分方程](./zh/examples/pirbn.md) | 机理驱动 | PIRBN | 无监督学习 | - | [Paper](https://arxiv.org/abs/2304.06234) | -| 微分方程 | [洛伦兹方程](./zh/examples/lorenz.md) | 数据驱动 | Transformer-Physx | 监督学习 | [Data](https://github.com/zabaras/transformer-physx) | [Paper](https://arxiv.org/abs/2010.03957) | -| 微分方程 | [若斯叻方程](./zh/examples/rossler.md) | 数据驱动 | Transformer-Physx | 监督学习 | [Data](https://github.com/zabaras/transformer-physx) | [Paper](https://arxiv.org/abs/2010.03957) | -| 算子学习 | [DeepONet](./zh/examples/deeponet.md) | 数据驱动 | MLP | 监督学习 | [Data](https://deepxde.readthedocs.io/en/latest/demos/operator/antiderivative_unaligned.html) | [Paper](https://export.arxiv.org/pdf/1910.03193.pdf) | -| 微分方程 | [梯度增强的物理知识融合 PDE 求解](https://github.com/PaddlePaddle/PaddleScience/blob/develop/examples/gpinn/poisson_1d.py) | 机理驱动 | gPINN | 无监督学习 | - | [Paper](https://doi.org/10.1016/j.cma.2022.114823) | -| 积分方程 | [沃尔泰拉积分方程](./zh/examples/volterra_ide.md) | 机理驱动 | MLP | 无监督学习 | - | [Project](https://github.com/lululxvi/deepxde/blob/master/examples/pinn_forward/Volterra_IDE.py) | -| 微分方程 | [分数阶微分方程](https://github.com/PaddlePaddle/PaddleScience/blob/develop/examples/fpde/fractional_poisson_2d.py) | 机理驱动 | MLP | 无监督学习 | - | - | -| 光孤子 | [Optical soliton](./zh/examples/nlsmb.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://doi.org/10.1007/s11071-023-08824-w)| -| 光纤怪波 | [Optical rogue wave](./zh/examples/nlsmb.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://doi.org/10.1007/s11071-023-08824-w)| -| 域分解 | [XPINN](./zh/examples/xpinns.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://doi.org/10.4208/cicp.OA-2020-0164)| -| 布鲁塞尔扩散系统 | [3D-Brusselator](./zh/examples/brusselator3d.md) | 数据驱动 | LNO | 监督学习 | - | [Paper](https://arxiv.org/abs/2303.10528)| - -
-

技术科学(AI for Technology)

- -| 问题类型 | 案例名称 | 优化算法 | 模型类型 | 训练方式 | 数据集 | 参考资料 | -|-----|---------|-----|---------|----|---------|---------| -| 一维线性对流问题 | [1D 线性对流](./zh/examples/adv_cvit.md) | 数据驱动 | ViT | 监督学习 | [Data](https://github.com/Zhengyu-Huang/Operator-Learning/tree/main/data) | [Paper](https://arxiv.org/abs/2405.13998) | -| 非定常不可压流体 | [2D 方腔浮力驱动流](./zh/examples/ns_cvit.md) | 数据驱动 | ViT | 监督学习 | [Data](https://huggingface.co/datasets/pdearena/NavierStokes-2D) | [Paper](https://arxiv.org/abs/2405.13998) | -| 定常不可压流体 | [Re3200 2D 定常方腔流](./zh/examples/ldc2d_steady.md) | 机理驱动 | MLP | 无监督学习 | - | | -| 定常不可压流体 | [2D 达西流](./zh/examples/darcy2d.md) | 机理驱动 | MLP | 无监督学习 | - | | -| 定常不可压流体 | [2D 管道流](./zh/examples/labelfree_DNN_surrogate.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://arxiv.org/abs/1906.02382) | -| 定常不可压流体 | [3D 颅内动脉瘤](./zh/examples/aneurysm.md) | 机理驱动 | MLP | 无监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/aneurysm/aneurysm_dataset.tar) | [Project](https://docs.nvidia.com/deeplearning/modulus/modulus-v2209/user_guide/intermediate/adding_stl_files.html)| -| 定常不可压流体 | [任意 2D 几何体绕流](./zh/examples/deepcfd.md) | 数据驱动 | DeepCFD | 监督学习 | - | [Paper](https://arxiv.org/abs/2004.08826)| -| 非定常不可压流体 | [2D 非定常方腔流](./zh/examples/ldc2d_unsteady.md) | 机理驱动 | MLP | 无监督学习 | - | -| -| 非定常不可压流体 | [Re100 2D 圆柱绕流](./zh/examples/cylinder2d_unsteady.md) | 机理驱动 | MLP | 半监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/cylinder2d_unsteady_Re100/cylinder2d_unsteady_Re100_dataset.tar) | [Paper](https://arxiv.org/abs/2004.08826)| -| 非定常不可压流体 | [Re100~750 2D 圆柱绕流](./zh/examples/cylinder2d_unsteady_transformer_physx.md) | 数据驱动 | Transformer-Physx | 监督学习 | [Data](https://github.com/zabaras/transformer-physx) | [Paper](https://arxiv.org/abs/2010.03957)| -| 可压缩流体 | [2D 空气激波](./zh/examples/shock_wave.md) | 机理驱动 | PINN-WE | 无监督学习 | [Data](https://aistudio.baidu.com/datasetdetail/167250) | -| -| 飞行器设计 | [MeshGraphNets](https://aistudio.baidu.com/projectdetail/5322713) | 数据驱动 | GNN | 监督学习 | [Data](https://aistudio.baidu.com/datasetdetail/184320) | [Paper](https://arxiv.org/abs/2010.03409)| -| 飞行器设计 | [火箭发动机真空羽流](https://aistudio.baidu.com/projectdetail/4486133) | 数据驱动 | CNN | 监督学习 | [Data](https://aistudio.baidu.com/datasetdetail/167250) | - | -| 飞行器设计 | [Deep-Flow-Prediction](https://aistudio.baidu.com/projectdetail/5671596) | 数据驱动 | TurbNetG | 监督学习 | [Data](https://aistudio.baidu.com/datasetdetail/197778) | [Paper](https://arxiv.org/abs/1810.08217) | -| 通用流场模拟 | [气动外形设计](./zh/examples/amgnet.md) | 数据驱动 | AMGNet | 监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/AMGNet/data.zip) | [Paper](https://arxiv.org/abs/1810.08217) | -| 流固耦合 | [涡激振动](./zh/examples/viv.md) | 机理驱动 | MLP | 半监督学习 | [Data](https://github.com/PaddlePaddle/PaddleScience/blob/develop/examples/fsi/VIV_Training_Neta100.mat) | [Paper](https://arxiv.org/abs/2206.03864)| -| 多相流 | [气液两相流](./zh/examples/bubble.md) | 机理驱动 | BubbleNet | 半监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/BubbleNet/bubble.mat) | [Paper](https://pubs.aip.org/aip/adv/article/12/3/035153/2819394/Predicting-micro-bubble-dynamics-with-semi-physics)| -| 多相流 | [twophasePINN](https://aistudio.baidu.com/projectdetail/5379212) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://doi.org/10.1016/j.mlwa.2021.100029)| -| 流场高分辨率重构 | [2D 湍流流场重构](./zh/examples/tempoGAN.md) | 数据驱动 | tempoGAN | 监督学习 | [Train Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/tempoGAN/2d_train.mat)
[Eval Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/tempoGAN/2d_valid.mat) | [Paper](https://dl.acm.org/doi/10.1145/3197517.3201304)| -| 流场高分辨率重构 | [2D 湍流流场重构](https://aistudio.baidu.com/projectdetail/4493261?contributionType=1) | 数据驱动 | cycleGAN | 监督学习 | [Train Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/tempoGAN/2d_train.mat)
[Eval Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/tempoGAN/2d_valid.mat) | [Paper](https://arxiv.org/abs/2007.15324)| -| 流场高分辨率重构 | [基于Voronoi嵌入辅助深度学习的稀疏传感器全局场重建](https://aistudio.baidu.com/projectdetail/5807904) | 数据驱动 | CNN | 监督学习 | [Data1](https://drive.google.com/drive/folders/1K7upSyHAIVtsyNAqe6P8TY1nS5WpxJ2c)
[Data2](https://drive.google.com/drive/folders/1pVW4epkeHkT2WHZB7Dym5IURcfOP4cXu)
[Data3](https://drive.google.com/drive/folders/1xIY_jIu-hNcRY-TTf4oYX1Xg4_fx8ZvD) | [Paper](https://arxiv.org/pdf/2202.11214.pdf) | -| 求解器耦合 | [CFD-GCN](./zh/examples/cfdgcn.md) | 数据驱动 | GCN | 监督学习 | [Data](https://aistudio.baidu.com/aistudio/datasetdetail/184778)
[Mesh](https://paddle-org.bj.bcebos.com/paddlescience/datasets/CFDGCN/meshes.tar) | [Paper](https://arxiv.org/abs/2007.04439)| -| 受力分析 | [1D 欧拉梁变形](./zh/examples/euler_beam.md) | 机理驱动 | MLP | 无监督学习 | - | - | -| 受力分析 | [2D 平板变形](./zh/examples/biharmonic2d.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://arxiv.org/abs/2108.07243) | -| 受力分析 | [3D 连接件变形](./zh/examples/bracket.md) | 机理驱动 | MLP | 无监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/bracket/bracket_dataset.tar) | [Tutorial](https://docs.nvidia.com/deeplearning/modulus/modulus-v2209/user_guide/foundational/linear_elasticity.html) | -| 受力分析 | [结构震动模拟](./zh/examples/phylstm.md) | 机理驱动 | PhyLSTM | 监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/PhyLSTM/data_boucwen.mat) | [Paper](https://arxiv.org/abs/2002.10253) | -| 受力分析 | [2D 弹塑性结构](./zh/examples/epnn.md) | 机理驱动 | EPNN | 无监督学习 | [Train Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/epnn/dstate-16-plas.dat)
[Eval Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/epnn/dstress-16-plas.dat) | [Paper](https://arxiv.org/abs/2204.12088) | -| 受力分析和逆问题 | [3D 汽车控制臂变形](./zh/examples/control_arm.md) | 机理驱动 | MLP | 无监督学习 | - | - | -| 拓扑优化 | [2D 拓扑优化](./zh/examples/topopt.md) | 数据驱动 | TopOptNN | 监督学习 | [Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/topopt/top_dataset.h5) | [Paper](https://arxiv.org/pdf/1709.09578) | -| 热仿真 | [1D 换热器热仿真](./zh/examples/heat_exchanger.md) | 机理驱动 | PI-DeepONet | 无监督学习 | - | - | -| 热仿真 | [2D 热仿真](./zh/examples/heat_pinn.md) | 机理驱动 | PINN | 无监督学习 | - | [Paper](https://arxiv.org/abs/1711.10561)| -| 热仿真 | [2D 芯片热仿真](./zh/examples/chip_heat.md) | 机理驱动 | PI-DeepONet | 无监督学习 | - | [Paper](https://doi.org/10.1063/5.0194245)| - -
-

材料科学(AI for Material)

- -| 问题类型 | 案例名称 | 优化算法 | 模型类型 | 训练方式 | 数据集 | 参考资料 | -|-----|---------|-----|---------|----|---------|---------| -| 材料设计 | [散射板设计(反问题)](./zh/examples/hpinns.md) | 数理融合 | 数据驱动 | 监督学习 | [Train Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/hPINNs/hpinns_holo_train.mat)
[Eval Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/hPINNs/hpinns_holo_valid.mat) | [Paper](https://arxiv.org/pdf/2102.04626.pdf) | - -
-

地球科学(AI for Earth Science)

- -| 问题类型 | 案例名称 | 优化算法 | 模型类型 | 训练方式 | 数据集 | 参考资料 | -|-----|---------|-----|---------|----|---------|---------| -| 天气预报 | [Extformer-MoE 气象预报](./zh/examples/extformer_moe.md) | 数据驱动 | FourCastNet | 监督学习 | [enso](https://tianchi.aliyun.com/dataset/98942) | - | -| 天气预报 | [FourCastNet 气象预报](./zh/examples/fourcastnet.md) | 数据驱动 | FourCastNet | 监督学习 | [ERA5](https://app.globus.org/file-manager?origin_id=945b3c9e-0f8c-11ed-8daf-9f359c660fbd&origin_path=%2F~%2Fdata%2F) | [Paper](https://arxiv.org/pdf/2202.11214.pdf) | -| 天气预报 | [NowCastNet 气象预报](./zh/examples/nowcastnet.md) | 数据驱动 | NowCastNet | 监督学习 | [MRMS](https://app.globus.org/file-manager?origin_id=945b3c9e-0f8c-11ed-8daf-9f359c660fbd&origin_path=%2F~%2Fdata%2F) | [Paper](https://www.nature.com/articles/s41586-023-06184-4) | -| 天气预报 | [GraphCast 气象预报](./zh/examples/graphcast.md) | 数据驱动 | GraphCastNet | 监督学习 | - | [Paper](https://arxiv.org/abs/2212.12794) | -| 大气污染物 | [UNet 污染物扩散](https://aistudio.baidu.com/projectdetail/5663515?channel=0&channelType=0&sUid=438690&shared=1&ts=1698221963752) | 数据驱动 | UNet | 监督学习 | [Data](https://aistudio.baidu.com/datasetdetail/198102) | - | -| 天气预报 | [DGMR 气象预报](./zh/examples/dgmr.md) | 数据驱动 | DGMR | 监督学习 | [UK dataset](https://huggingface.co/datasets/openclimatefix/nimrod-uk-1km) | [Paper](https://arxiv.org/pdf/2104.00954.pdf) | -| 地震波形反演 | [VelocityGAN 地震波形反演](./zh/examples/velocity_gan.md) | 数据驱动 | VelocityGAN | 监督学习 | [OpenFWI](https://openfwi-lanl.github.io/docs/data.html#vel) | [Paper](https://arxiv.org/abs/1809.10262v6) | - -## 🚀快速安装 - -=== "方式1: 源码安装[推荐]" - - --8<-- - ./README.md:git_install - --8<-- - -=== "方式2: pip安装" - - ``` sh - pip install -U paddlesci - ``` - -**完整安装流程**:[安装与使用](./zh/install_setup.md) - ---8<-- -./README.md:update ---8<-- - ---8<-- -./README.md:feature ---8<-- - -## 🎈生态工具 - ---8<-- -./README.md:adaptation ---8<-- - ---8<-- -./README.md:support ---8<-- - ---8<-- -./README.md:contribution ---8<-- - ---8<-- -./README.md:collaboration ---8<-- - ---8<-- -./README.md:thanks ---8<-- - -- PaddleScience 的部分代码由以下优秀开发者贡献(按 [Contributors](https://github.com/PaddlePaddle/PaddleScience/graphs/contributors) 排序): - - -
- -## 🤝合作单位 - -![cooperation](./images/overview/cooperation.png) - ---8<-- -./README.md:license ---8<-- +
\ No newline at end of file diff --git a/docs/javascripts/arxiv.js b/docs/javascripts/arxiv.js new file mode 100644 index 000000000..ab81169fb --- /dev/null +++ b/docs/javascripts/arxiv.js @@ -0,0 +1,45 @@ +// 假设这是从某个地方获取的 arXiv 搜索结果,通常你会通过 AJAX 请求或者 fetch API 获取这个数据 +const arxivResults = [ + { + title: 'Example Paper Title 1', + authors: ['Author1', 'Author2'], + abstract: 'This is the abstract of the first example paper.', + link: 'https://arxiv.org/abs/example1' + }, + { + title: 'Example Paper Title 2', + authors: ['Author3', 'Author4'], + abstract: 'This is the abstract of the second example paper.', + link: 'https://arxiv.org/abs/example2' + } + // ... more results +]; + +// 获取页面上的某个元素来展示搜索结果 +const resultsDiv = document.getElementById('arxiv-papers'); + +// 遍历搜索结果,并为每个结果创建一个展示元素 +arxivResults.forEach(result => { + const articleDiv = document.createElement('div'); + articleDiv.classList.add('article'); + + const title = document.createElement('h3'); + title.textContent = result.title; + articleDiv.appendChild(title); + + const authors = document.createElement('p'); + authors.textContent = `Authors: ${result.authors.join(', ')}`; + articleDiv.appendChild(authors); + + const abstract = document.createElement('p'); + abstract.textContent = `Abstract: ${result.abstract}`; + articleDiv.appendChild(abstract); + + const link = document.createElement('a'); + link.href = result.link; + link.textContent = 'View on arXiv'; + articleDiv.appendChild(link); + + // 将创建好的元素添加到页面上 + resultsDiv.appendChild(articleDiv); +}); \ No newline at end of file diff --git a/docs/zh/biology_medicine.md b/docs/zh/biology_medicine.md new file mode 100644 index 000000000..b8c5a9c68 --- /dev/null +++ b/docs/zh/biology_medicine.md @@ -0,0 +1,41 @@ +[【PaddleHelix】螺旋桨生物计算开源工具集](https://aistudio.baidu.com/aistudio/projectdetail/1293361?channelType=0&channel=0&sUid=14197935&ts=1731058781419) + +[使用螺旋桨PaddleHelix完成RNA结构预测竞赛的前置基础知识整理](https://aistudio.baidu.com/aistudio/projectdetail/1404818?channelType=0&channel=0&sUid=14197935&ts=1731058794651) + +[深度学习还能做药物研发?PaddleHelix手把手教你蛋白质和化合物作用预测](https://aistudio.baidu.com/aistudio/projectdetail/1335347?channelType=0&channel=0&sUid=14197935&ts=1731058802955) + +[PaddleHelix工具集应用: 分子生成](https://aistudio.baidu.com/aistudio/projectdetail/1936495?channelType=0&channel=0&sUid=14197935&ts=1731059246459) + +[PaddleHelix工具集应用: 化合物属性预测](https://aistudio.baidu.com/aistudio/projectdetail/1332652?channelType=0&channel=0&sUid=14197935&ts=1731059263808) + +[基于PaddleHelix完成RNA结构预测运行环境v2.0](https://aistudio.baidu.com/aistudio/projectdetail/1486205?channelType=0&channel=0&sUid=14197935&ts=1731059279016) + +[PaddleHelix工具集应用: 蛋白质预训练及属性预测](https://aistudio.baidu.com/aistudio/projectdetail/1333636?channelType=0&channel=0&sUid=14197935&ts=1731059287891) + +[【PaddleHelix】AI药物研发算法大赛ViSNet-Drug复赛解决方案](https://aistudio.baidu.com/aistudio/projectdetail/6695841?channelType=0&channel=0&sUid=14197935&ts=1731059297921) + +[【PaddleHelix】AI药物研发算法大赛paipai决赛解决方案](https://aistudio.baidu.com/aistudio/projectdetail/6685523?channelType=0&channel=0&sUid=14197935&ts=1731059312270) + +[PP-HelixFold_体验1](https://aistudio.baidu.com/aistudio/projectdetail/5487506?channelType=0&channel=0&sUid=14197935&ts=1731059432502) + +[PaddleHelix工具集应用: 分子生成](https://aistudio.baidu.com/aistudio/projectdetail/1985171?channelType=0&channel=0&sUid=14197935&ts=1731059451410) + +[RNA二级结构预测](https://aistudio.baidu.com/aistudio/projectdetail/1335221?channelType=0&channel=0&sUid=14197935&ts=1731059461282) + +[药物-分子作用预测](https://aistudio.baidu.com/aistudio/projectdetail/1431027?channelType=0&channel=0&sUid=14197935&ts=1731059472191) + +[螺旋桨RNA结构预测竞赛第一名方案](https://aistudio.baidu.com/aistudio/projectdetail/1479469?channelType=0&channel=0&sUid=14197935&ts=1731059492005) + +[AI for Science | 生物学年龄评价与年龄相关疾病风险预测](https://aistudio.baidu.com/aistudio/projectdetail/6650614?channelType=0&channel=0&sUid=14197935&ts=1731059971274) + +[基于百度AI Studio的药物设计——NAMD自由能微扰计算(FEP笔记本)](https://aistudio.baidu.com/aistudio/projectdetail/4326115?channelType=0&channel=0&sUid=14197935&ts=1731060625811) + +[蛋白质分子动力学模拟1-NAMD with GPU](https://aistudio.baidu.com/aistudio/projectdetail/1850669?channelType=0&channel=0&sUid=14197935&ts=1731060778386) + +[eemd-stft-cnn-EEG信号麻醉深度识别](https://aistudio.baidu.com/aistudio/projectdetail/4450917?channelType=0&channel=0&sUid=14197935&ts=1731060934153) + +[Protein-ligand MD simulation](https://aistudio.baidu.com/aistudio/projectdetail/4621684?channelType=0&channel=0&sUid=14197935&ts=1731060960311) + +[医学影像数据集集锦](https://aistudio.baidu.com/aistudio/projectdetail/462184?channelType=0&channel=0&sUid=14197935&ts=1731060976805) + +[基于紫外差分吸收光谱技术与神经网络结合的呼出气体中氨气的检测](https://aistudio.baidu.com/aistudio/projectdetail/8190914?channelType=0&channel=0&sUid=14197935&ts=1731058813858) diff --git a/docs/zh/chemistry_material_science.md b/docs/zh/chemistry_material_science.md new file mode 100644 index 000000000..6dd9080c3 --- /dev/null +++ b/docs/zh/chemistry_material_science.md @@ -0,0 +1,19 @@ +[材料缺陷检测](https://aistudio.baidu.com/aistudio/projectdetail/3482461?channelType=0&channel=0&sUid=14197935&ts=1731059563182) + +[使用Paddle框架实现晶圆缺陷图片相似度推荐](https://aistudio.baidu.com/aistudio/projectdetail/5818368?channelType=0&channel=0&sUid=14197935&ts=1731059764951) + +[飞桨AI Studio星河社区-人工智能学习与实训社区](https://aistudio.baidu.com/clusterprojectdetail/7677668) + +[有机均裂键解离的预测 接近化学精度的焓值 亚秒计算成本](https://aistudio.baidu.com/aistudio/projectdetail/2283177?channelType=0&channel=0&sUid=14197935&ts=1731060415231) + +[【论文复现第六期】飞桨分子动力学模拟PaddleMD-复现TorchMD](https://aistudio.baidu.com/aistudio/projectdetail/3863645?channelType=0&channel=0&sUid=14197935&ts=1731060484519) + +[漫游百度量子平台之一-变分量子本征求解器(VQE)量桨版](https://aistudio.baidu.com/aistudio/projectdetail/2128294?channelType=0&channel=0&sUid=14197935&ts=1731060510116) + +[DeePMD-kit](https://aistudio.baidu.com/aistudio/projectdetail/2510942?channelType=0&channel=0&sUid=14197935&ts=1731060529292) + +[DeePMD-kit-分子模拟框架](https://aistudio.baidu.com/aistudio/projectdetail/1944454?channelType=0&channel=0&sUid=14197935&ts=1731060545976) + +[GPUMD分子动力学-学习与实践](https://aistudio.baidu.com/aistudio/projectdetail/294632?channelType=0&channel=0&sUid=14197935&ts=1731061115777) + +[走进量子计算的大门——使用量桨PaddleQuantum创建单量子比特门](https://aistudio.baidu.com/aistudio/projectdetail/6922870?channelType=0&channel=0&sUid=14197935&ts=1731058772887) diff --git a/docs/zh/competition.md b/docs/zh/competition.md new file mode 100644 index 000000000..80b41ccaa --- /dev/null +++ b/docs/zh/competition.md @@ -0,0 +1,9 @@ +# 比赛 + +[开放原子第二届开源大赛:飞桨科学计算工具组件开发大赛](https://competition.atomgit.com/competitionInfo?id=805ad94637707d062f24e54265d85731),总奖金25万人民币,火热报名中。 + +[PaddlePaddle Hackathon 7th 开源贡献个人挑战赛](https://github.com/PaddlePaddle/Paddle/issues/67603) + +[CIKM 2024: AI辅助的先进空气动力学-优化汽车设计以实现最佳性能](https://competition.atomgit.com/competitionInfo?id=cda4e961b0c25858ca0fd2a4bdf87520),已进入评奖阶段。 + +[IJCAI 2024: 任意三维几何外形车辆的风阻快速预测竞赛](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5),track A, B, C 代码:[paddle实现](https://github.com/PaddlePaddle/PaddleScience/tree/develop/jointContribution/IJCAI_2024) | [pytorch实现](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5)(点击**排行榜**可查看各个赛道前10名的代码) \ No newline at end of file diff --git a/docs/zh/earth_science.md b/docs/zh/earth_science.md new file mode 100644 index 000000000..c11db9c64 --- /dev/null +++ b/docs/zh/earth_science.md @@ -0,0 +1,9 @@ +[飞桨黑客马拉松第五期 Graphcast- AI驱动的中期全球天气预报](https://aistudio.baidu.com/projectdetail/7266127?channelType=0&channel=0) + +[飞桨黑客马拉松第四期 RegAE-Paddle 基于VAE的水文逆分析正则化方法](https://aistudio.baidu.com/aistudio/projectdetail/5541961?channelType=0&channel=0&sUid=14197935&ts=1731060045596) + +[科学计算案例:基于PaddleScience的FourCastNet模型实现气象](https://aistudio.baidu.com/projectdetail/6213922?contributionType=1&sUid=455441&shared=1&ts=1684585396793) + +[【AI for Science 共创计划】Nested FNO 复现论文](https://aistudio.baidu.com/projectdetail/7390303) + +[科学计算(AI4S): 基于PaddleScience的PINN实现介电常数设计](https://aistudio.baidu.com/projectdetail/6390502) \ No newline at end of file diff --git a/docs/zh/fluid_mechanics.md b/docs/zh/fluid_mechanics.md new file mode 100644 index 000000000..079540320 --- /dev/null +++ b/docs/zh/fluid_mechanics.md @@ -0,0 +1,82 @@ + +[科学计算案例:基于PaddleScience的Cylinder2D问题求解](https://aistudio.baidu.com/projectdetail/6178818?sUid=455441&shared=1&ts=1684397945680) + +[基于PaddleScience+CVit的advection方程求解](https://aistudio.baidu.com/projectdetail/8141430) + +[共创计划:基于 PINN 方法求解可压缩流体欧拉方程组的正问题](https://aistudio.baidu.com/projectdetail/7593837) + +[拉格朗日粒子流体Benchmark开源数据集](https://aistudio.baidu.com/projectdetail/7507477) + +[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7309026) + +[DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/5489960?channelType=0&channel=0) + +[AI for Science 共创计划 AMGNET 论文复现](https://aistudio.baidu.com/projectdetail/5592458?channelType=0&channel=0) + +[AI for Science 共创计划GNN Laminar Flow 论文复现](https://aistudio.baidu.com/projectdetail/5563934?channelType=0&channel=0) + +[共创计划:基于Transformer架构的流体流动降阶模拟的研究](https://aistudio.baidu.com/projectdetail/7509905) + +[[论文复现赛第七期] 54 - CycleGAN 湍流超分辨率重建](https://aistudio.baidu.com/projectdetail/4493261?channelType=0&channel=0) + +[【论文复现】基于神经微分方程的流体降阶模型(超详细讲解Neural ODE)](https://aistudio.baidu.com/projectdetail/5680422?searchKeyword=%E8%B6%85%E8%AF%A6%E7%BB%86%E8%AE%B2%E8%A7%A3ODE&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience的LDC2D(瞬态)求解](https://aistudio.baidu.com/projectdetail/6160749?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience实现稳态LDC2D求解](https://aistudio.baidu.com/projectdetail/6137973?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience的2维圆柱绕流求解](https://aistudio.baidu.com/projectdetail/6160381?searchKeyword=AI4S&searchTab=ALL) + +[AI For Science— 基于AI求解2D非定常圆柱绕流,真的很流体!!](https://aistudio.baidu.com/projectdetail/4178470?channelType=0&channel=0) + +[AI for Science - 基于PINN的圆柱绕流模型优化策略分析](https://aistudio.baidu.com/projectdetail/5139786?channelType=0&channel=0) + +[PaddleScience-2D非定常圆柱绕流案例训练过程行为分析](https://aistudio.baidu.com/projectdetail/5042739?searchKeyword=paddlescience-2d&searchTab=PROJECT) + +[科学计算-为 2D 非定常圆柱绕流案例调优精度](https://aistudio.baidu.com/projectdetail/4529544?channelType=0&channel=0) + +[科学计算——减少 PaddleScience 2D 非定常圆柱绕流案例的监督数据](https://aistudio.baidu.com/projectdetail/4501565?channelType=0&channel=0) + +[科学计算(AI4S): 基于PaddleScience的二维激波仿真](https://aistudio.baidu.com/projectdetail/6755993?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience实现DarcyFlow](https://aistudio.baidu.com/projectdetail/6184070?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PI-DeepONet模型的芯片热仿真](https://aistudio.baidu.com/projectdetail/7682679?channelType=0&channel=0) + +[基于PaddlePaddle的DeepCFD复现](https://aistudio.baidu.com/projectdetail/4400677?channelType=0&channel=0) + +[Voronoi_CNN_with_PaddlePaddle](https://aistudio.baidu.com/projectdetail/5807904?searchKeyword=Voronoi&searchTab=ALL) + +[Compressible PINN](https://aistudio.baidu.com/projectdetail/5528154?channelType=0&channel=0) + +[ldc_project](https://aistudio.baidu.com/projectdetail/4458545?channelType=0&channel=0) + +[基于PINN的传播动力学研究](https://aistudio.baidu.com/projectdetail/5794004?searchKeyword=%E4%BC%A0%E6%92%AD%E5%8A%A8%E5%8A%9B%E5%AD%A6%E7%A0%94%E7%A9%B6&searchTab=ALL) + +[基于飞桨实现火箭发动机真空羽流流场的快速计算](https://aistudio.baidu.com/projectdetail/4486133?channelType=0&channel=0) + +[AI4S共创计划:基于数据驱动的污染物扩散深度学习模型案例](https://aistudio.baidu.com/projectdetail/5663515?channelType=0&channel=0) + +[[论文复现赛] MeshGraphNets Paddle复现](https://aistudio.baidu.com/projectdetail/5322713?channelType=0&channel=0) + +[飞桨黑客马拉松第四期 针对RANS方程的深度学习机翼翼型优化方法](https://aistudio.baidu.com/projectdetail/5671596?searchKeyword=%E9%92%88%E5%AF%B9RANS%E6%96%B9%E7%A8%8B&searchTab=ALL) + +[飞桨论文复现营 CFDGCN-Paddle](https://aistudio.baidu.com/projectdetail/5216848?channelType=0&channel=0) + +[NSFNet1-3](https://aistudio.baidu.com/projectdetail/7305373) + +[科学计算(AI4S): 基于PaddleScience的VIV方程求解](https://aistudio.baidu.com/projectdetail/6160556?searchKeyword=AI4S&searchTab=ALL) + +[PhyGeoNet](https://aistudio.baidu.com/projectdetail/7195983) + +[科学计算(AI4S): 基于PaddleScience实现流体超分](https://aistudio.baidu.com/aistudio/projectdetail/6521709) + +[PhyCRNet](https://aistudio.baidu.com/projectdetail/7296776) + +[科学计算(AI4S): 基于PaddleScience的3D布鲁塞尔求解](https://aistudio.baidu.com/projectdetail/8347444) + +[飞桨AI Studio星河社区-人工智能学习与实训社区](https://aistudio.baidu.com/projectdetail/8517330?forkThirdPart=1) + +[twophasePINN with PaddlePaddle](https://aistudio.baidu.com/projectdetail/5379212) + +[NSFNet4](https://aistudio.baidu.com/projectdetail/7305374) \ No newline at end of file diff --git a/docs/zh/get_link.py b/docs/zh/get_link.py new file mode 100644 index 000000000..5c99f79da --- /dev/null +++ b/docs/zh/get_link.py @@ -0,0 +1,42 @@ +# coding=utf-8 + +import pandas as pd +from openpyxl import load_workbook + +# 读取 Excel 文件 +file_path = '工作簿4.xlsx' +wb = load_workbook(file_path, data_only=True) +sheet = wb.active # 或者使用 wb['SheetName'] 来指定特定的 sheet + +# 创建一个空的 DataFrame 来存储数据 +df = pd.DataFrame() +key_list = [] +value_list = [] +# 遍历所有行和列 +i = 0 +for row in sheet.iter_rows(min_row=2, values_only=False): # min_row=2 从第二行开始 + print("row: ", i) + i = i+1 + row_data = [] + for cell in row: + if cell.hyperlink: # 检查单元格是否有超链接 + row_data.append(cell.hyperlink) # 添加超链接的 URL + cell.value = cell.value.replace(" - 飞桨AI Studio星河社区", '') + cell.value = cell.value.replace("", '') + print(cell.value) #打印cell name + print(cell.hyperlink.display) + key_list.append(cell.value) + value_list.append(cell.hyperlink.display) + else: + row_data.append(cell.value) # 添加单元格的值 + +n = len(value_list) + +with open('notebooks.md', 'w', encoding='utf-8') as file: + # 遍历字典的 key 和 value + for i in range(n): + # 按照 [key](value) 的格式写入文件 + file.write(f'[{key_list[i]}]({value_list[i]})\n\n') + +# 打印 DataFrame +print(df) \ No newline at end of file diff --git a/docs/zh/notebooks.md b/docs/zh/notebooks.md new file mode 100644 index 000000000..48332b445 --- /dev/null +++ b/docs/zh/notebooks.md @@ -0,0 +1,11 @@ +[Biology & Medicine](biology_medicine.md) + +[Fluid Mechanics](fluid_mechanics.md) + +[Chemistry & Material Science](chemistry_material_science.md) + +[Structral Mechanics](structral_mechanics.md) + +[Partial Differential Equation](pde.md) + +[Earth Science](earth_science.md) \ No newline at end of file diff --git a/docs/zh/overview.md b/docs/zh/overview.md deleted file mode 100644 index 1029c9600..000000000 --- a/docs/zh/overview.md +++ /dev/null @@ -1,123 +0,0 @@ -# PaddleScience 模块介绍 - -PaddleScience 在代码结构上划分为 12 个模块。从一般深度学习工作流的角度来看,这 12 个模块分别负责构建输入数据、构建神经网络模型、构建损失函数、构建优化器,训练、评估、可视化等功能。从科学计算角度来看,部分模块承担了不同于 CV、NLP 任务的功能,比如用于物理机理驱动的 Equation 模块,定义方程公式和辅助高阶微分计算;用于涉及几何场景采样的 Geometry 模块,定义简单、复杂几何形状并在其内部、边界采样构造数据;Constraint 模块将不同的优化目标视为一种“约束”,使得套件能用一套训练代码统一物理机理驱动、数据驱动、数理融合三种不同的求解流程。 - - -panorama - - -## 1. 整体工作流 - -
- ![workflow](../images/overview/workflow.jpg){ loading=lazy style="height:80%;width:80%"} -
- -上图是 PaddleScience 的 workflow 示意图(以基于几何的问题求解为例),流程描述如下 - -1. Geometry 负责构建几何并在几何上采样,完成数据构建; -2. 用 Model 模块接受输入,得到模型输出; -3. 科学计算任务具有特殊性,模型输出往往并不是前向计算的终点,还需要进一步按照 Equation,计算出方程公式所需的变量; -4. 计算损失函数,并利用框架的自动微分机制,求出所有参数的梯度; -5. 上述的优化目标可以施加在几何的不同区域上,比如interior、boundary区域,因此上图中的 Constraint 可以有多个; -6. 将所有 Constraint 贡献的梯度累加,并用于更新模型参数; -7. 训练过程中如果开启了评估和可视化功能,则会按一定频率自动对当前模型进行评估和预测结果可视化; -8. Solver 是整个套件运行的全局调度模块,负责将上述过程按用户指定的轮数和频率重复运行。 - -## 2. 模块简介 - -### 2.1 [Arch](./api/arch.md) - -Arch 模块负责各种神经网络模型的组网、参数初始化、前向计算等功能,内置了多种模型供用户使用。 - -### 2.2 [AutoDiff](./api/autodiff.md) - -AutoDiff 模块负责计算高阶微分功能,内置基于 Paddle 自动微分机制的全局单例 `jacobian`、`hessian` 供用户使用。 - -### 2.3 [Constraint](./api/constraint.md) - -
- ![constraint](../images/overview/constraint.jpg){ loading=lazy style="height:50%;width:50%"} -
- -为了在套件中统一物理信息驱动、数据驱动、数理融合三种求解方式,我们将数据构造、输入到输出的计算过程、损失函数等必要接口在其定义完毕之后,统一记录在 Constraint 这一模块中,有了这些接口,Constraint 就能表示不同的训练目标,如: - -- `InteriorConstraint` 定义了在给定的几何区域内部,按照给定输入到输出的计算过程,利用损失函数优化模型参数,使得模型输出满足给定的条件; -- `BoundaryConstraint` 定义了在给定的几何区域边界上,按照给定输入到输出的计算过程,利用损失函数优化模型参数,使得模型输出满足给定的条件; -- `SupervisedConstraint` 定义了在给定的监督数据(相当于CV、NLP中的监督训练)上,按照给定输入到输出的计算过程,利用损失函数优化模型参数,使得模型输出满足给定的条件。 -- ... - -这一模块有两个主要作用,一是在代码流程上统一了物理信息驱动、数据驱动两个不同的优化范式(前者类似监督训练方式,后者类似无监督训练方式),二是使得套件能应用在数理融合的场景中,只需分别构造不同的 Constraint 并让它们共同参与训练即可。 - -### 2.4 Data - -Data 模块负责数据的读取、包装和预处理,如下所示。 - -| 子模块名称 | 子模块功能 | -| :-- | :-- | -| [ppsci.data.dataset](./api/data/dataset.md)| 数据集相关 | -| [ppsci.data.transform](./api/data/process/transform.md)| 单个数据样本预处理相关方法 | -| [ppsci.data.batch_transform](./api/data/process/batch_transform.md)| 批数据预处理相关方法 | - -### 2.5 [Equation](./api/equation.md) - -
- ![equation](../images/overview/equation.jpg){ loading=lazy style="height:80%;width:80%"} -
- -Equation 模块负责定义各种常见方程的计算函数,如 `NavierStokes` 表示 N-S 方程,`Vibration` 表示振动方程,每个方程内部含有相关变量的计算函数。 - -### 2.6 [Geometry](./api/geometry.md) - -
- ![geometry](../images/overview/geometry.jpg#center){ loading=lazy style="height:50%;width:50%" } -
- -Geometry 模块负责定义各种常见的几何形状,如 `Interval` 线段几何、`Rectangle` 矩形几何、`Sphere` 球面几何。 - -### 2.7 [Loss](./api/loss/loss.md) - -Loss 模块包含 [`ppsci.loss.loss`](./api/loss/loss.md) 与 [`ppsci.loss.mtl`](./api/loss/mtl.md) 两个子模块,如下所示。 - -| 子模块名称 | 子模块功能 | -| :-- | :-- | -| [ppsci.loss.loss](./api/loss/loss.md)| 损失函数相关 | -| [ppsci.loss.mtl](./api/loss/mtl.md)| 多目标优化相关 | - -### 2.8 Optimizer - -Optimizer 模块包含 [`ppsci.optimizer.optimizer`](./api/optimizer.md) 与 [`ppsci.optimizer.lr_scheduler`](./api/lr_scheduler.md) 两个子模块,如下所示。 - -| 子模块名称 | 子模块功能 | -| :-- | :-- | -| [ppsci.utils.optimizer](./api/optimizer.md)| 优化器相关 | -| [ppsci.utils.lr_scheduler](./api/lr_scheduler.md)| 学习率调节器相关 | - -### 2.9 [Solver](./api/solver.md) - -Solver 模块负责定义求解器,作为训练、评估、推理、可视化的启动和管理引擎。 - -### 2.10 Utils - -Utils 模块内部存放了一些适用于多种场景下的工具类、函数,例如在 `reader.py` 下的数据读取函数,在 `logger.py` 下的日志打印函数,以及在 `expression.py` 下的方程计算类。 - -根据其功能细分为以下 8 个子模块 - -| 子模块名称 | 子模块功能 | -| :-- | :-- | -| [ppsci.utils.checker](./api/utils/checker.md)| ppsci 安装功能检查相关 | -| [ppsci.utils.expression](./api/utils/expression.md)| 负责训练、评估、可视化过程中涉及模型、方程的前向计算 | -| [ppsci.utils.initializer](./api/utils/initializer.md)| 常用参数初始化方法 | -| [ppsci.utils.logger](./api/utils/logger.md)| 日志打印模块 | -| [ppsci.utils.misc](./api/utils/misc.md)| 存放通用函数 | -| [ppsci.utils.reader](./api/utils/reader.md)| 文件读取模块 | -| [ppsci.utils.writer](./api/utils/writer.md)| 文件写入模块 | -| [ppsci.utils.save_load](./api/utils/save_load.md)| 模型参数保存与加载 | -| [ppsci.utils.symbolic](./api/utils/symbolic.md)| sympy 符号计算功能相关 | - -### 2.11 [Validate](./api/validate.md) - -Validator 模块负责定义各种评估器,用于在指定数据上进行评估(可选,默认不开启训练时评估),并得到评估指标。 - -### 2.12 [Visualize](./api/visualize.md) - -Visualizer 模块负责定义各种可视化器,用于模型评估完后在指定数据上进行预测(可选,默认不开启训练时可视化)并将结果保存成可视化的文件。 diff --git a/docs/zh/pde.md b/docs/zh/pde.md new file mode 100644 index 000000000..4b0494c64 --- /dev/null +++ b/docs/zh/pde.md @@ -0,0 +1,27 @@ +[科学计算(AI4S): 基于PaddleScience实现DeepONet](https://aistudio.baidu.com/projectdetail/6566389?channelType=0&channel=0) + +[数据驱动AI模型的PDE方程可解释性评估](https://aistudio.baidu.com/projectdetail/7463477?channelType=0&channel=0) + +[科学计算(AI4S): 基于PaddleScience实现SPINN](https://aistudio.baidu.com/projectdetail/8219967?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience+CVit的NS方程求解](https://aistudio.baidu.com/projectdetail/8141482?searchKeyword=AI4S&searchTab=ALL) + +[科学计算(AI4S): 基于PaddleScience的NLS_MB方程求解](https://aistudio.baidu.com/projectdetail/8043128?channelType=0&channel=0) + +[科学计算(AI4S): 基于PaddleScience的Volterra方程求解](https://aistudio.baidu.com/projectdetail/6622866?searchKeyword=Volterra&searchTab=ALL) + +[科学计算案例:基于PaddleScience的Laplace2D方程求解](https://aistudio.baidu.com/projectdetail/6169897?sUid=455441&shared=1&ts=1684122038217) + +[海光异构智能计算实践案例:基于 PaddleScience 的对流-扩散-反应](https://aistudio.baidu.com/projectdetail/6572117?channelType=0&channel=0) + +[科学计算(AI4S): 基于PaddleScience的Allen-Cahn求解](https://aistudio.baidu.com/projectdetail/7927786) + +[共创计划:基于连续演化数据预测双曲方程间断解](https://aistudio.baidu.com/projectdetail/7620492) + +[科学计算(AI4S): 基于PaddleScience实现SPINN](https://aistudio.baidu.com/projectdetail/8219967) + +[科学计算案例:基于PaddleScience的Rossler方程求解](https://aistudio.baidu.com/aistudio/projectdetail/6209280?sUid=455441&shared=1&ts=1684495132419) + +[科学计算案例:基于PaddleScience的Lorenz方程求解](https://aistudio.baidu.com/projectdetail/6206798?contributionType=1&sUid=455441&shared=1&ts=1684477535039) + +[科学计算(AI4S): 基于PaddleScience实现Burger方程求解](https://aistudio.baidu.com/aistudio/projectdetail/6508962) \ No newline at end of file diff --git a/docs/zh/structral_mechanics.md b/docs/zh/structral_mechanics.md new file mode 100644 index 000000000..9b9e9bec3 --- /dev/null +++ b/docs/zh/structral_mechanics.md @@ -0,0 +1,3 @@ +[DeepXDE薄板弯曲变形](https://aistudio.baidu.com/projectdetail/5792325?searchKeyword=Deepxde%E8%96%84%E6%9D%BF&searchTab=ALL) + +[PaddleScience-TopOpt](https://aistudio.baidu.com/projectdetail/6956236) \ No newline at end of file diff --git a/docs/zh/tutorials.md b/docs/zh/tutorials.md index 0ef12e726..0d7d95b91 100644 --- a/docs/zh/tutorials.md +++ b/docs/zh/tutorials.md @@ -1,6 +1,3 @@ -# 学习资料 - -## 教程课件 - - [深度学习技术与科学计算](https://aistudio.baidu.com/course/introduce/29929?sharedType=1&sharedUserId=438690&ts=1705731573142) + - [飞桨AI for Science流体力学公开课第一期](https://aistudio.baidu.com/course/introduce/27926?sharedType=1&sharedUserId=438690&ts=1705892946215) diff --git a/mkdocs.yml b/mkdocs.yml index 4d5d753b0..016e7c13e 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -13,8 +13,7 @@ # limitations under the License. # Project information -site_name: PaddleScience Docs -site_description: An out-of-the-box open source library for scientific computing based on deep learning. +site_name: 科研工作站 site_author: PaddlePaddle site_url: "https://github.com/PaddlePaddle/PaddleScience" edit_uri: edit/develop/docs/ @@ -29,12 +28,12 @@ copyright: Copyright © 2022 - 2023 PaddlePaddle # Page tree nav: - - PaddleScience: - - 主页: index.md - - 功能介绍: zh/overview.md - - 安装使用: zh/install_setup.md - - 快速开始: zh/quickstart.md - - 学习资料: zh/tutorials.md + - 科研工作站: + - " ": + - 论文检索: index.md + - Notebooks: zh/notebooks.md + - 比赛: zh/competition.md + - 课程: zh/tutorials.md - 经典案例: - " ": - 数学(AI for Math): @@ -98,51 +97,8 @@ nav: - VelocityGAN: zh/examples/velocity_gan.md - 化学科学(AI for Chemistry): - Moflow: zh/examples/moflow.md - - - API 文档: - - ppsci: - - ppsci.arch: zh/api/arch.md - - ppsci.autodiff: zh/api/autodiff.md - - ppsci.constraint: zh/api/constraint.md - - ppsci.data: - - ppsci.data.dataset: zh/api/data/dataset.md - - ppsci.data.transform: zh/api/data/process/transform.md - - ppsci.data.batch_transform: zh/api/data/process/batch_transform.md - - ppsci.equation: zh/api/equation.md - - ppsci.geometry: zh/api/geometry.md - - ppsci.loss: - - ppsci.loss.loss: zh/api/loss/loss.md - - ppsci.loss.mtl: zh/api/loss/mtl.md - - ppsci.metric: zh/api/metric.md - - ppsci.optimizer: - - ppsci.optimizer.optimizer: zh/api/optimizer.md - - ppsci.optimizer.lr_scheduler: zh/api/lr_scheduler.md - - ppsci.solver: zh/api/solver.md - - ppsci.utils: - - ppsci.utils.checker: zh/api/utils/checker.md - - ppsci.utils.expression: zh/api/utils/expression.md - - ppsci.utils.initializer: zh/api/utils/initializer.md - - ppsci.utils.logger: zh/api/utils/logger.md - - ppsci.utils.misc: zh/api/utils/misc.md - - ppsci.utils.ema: zh/api/utils/ema.md - - ppsci.utils.reader: zh/api/utils/reader.md - - ppsci.utils.writer: zh/api/utils/writer.md - - ppsci.utils.save_load: zh/api/utils/save_load.md - - ppsci.utils.symbolic: zh/api/utils/symbolic.md - - ppsci.validate: zh/api/validate.md - - ppsci.visualize: zh/api/visualize.md - - ppsci.experimental: zh/api/experimental.md - - ppsci.probability: zh/api/probability.md - - deploy: - - deploy.python_infer: zh/api/depoly/python_infer.md - - 使用指南: zh/user_guide.md - - 开发与复现指南: - - 开发指南: zh/development.md - - 复现指南: zh/reproduction.md - 学术成果: zh/academic.md - - 技术稿件: zh/technical_doc.md - 共创计划: zh/cooperation.md - - 实训社区: https://aistudio.baidu.com/aistudio/projectoverview/public?topic=15 # Configuration theme: @@ -240,6 +196,7 @@ extra_javascript: - javascripts/bd_statistics.js - javascripts/mathjax.js - javascripts/contributors.js + - javascripts/arxiv.js - https://polyfill.io/v3/polyfill.min.js?features=es6 - https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js From e768a01a3cbd54ebd9c4570f37164c69f4c35738 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Tue, 12 Nov 2024 13:32:44 +0800 Subject: [PATCH 02/10] arxiv search --- docs/index.md | 43 ++++++++----- docs/javascripts/arxiv.js | 128 +++++++++++++++++++++++++++++--------- docs/zh/competition.md | 2 +- 3 files changed, 126 insertions(+), 47 deletions(-) diff --git a/docs/index.md b/docs/index.md index 9a2258021..2886486df 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,16 +1,29 @@ -# PaddleScience - -
\ No newline at end of file + +
+ Title +
+ +
+ +
+
+
+ + \ No newline at end of file diff --git a/docs/javascripts/arxiv.js b/docs/javascripts/arxiv.js index ab81169fb..1dd72c893 100644 --- a/docs/javascripts/arxiv.js +++ b/docs/javascripts/arxiv.js @@ -1,4 +1,100 @@ -// 假设这是从某个地方获取的 arXiv 搜索结果,通常你会通过 AJAX 请求或者 fetch API 获取这个数据 +/* Copyright (c) 2016 Frase + * + * Distributed under MIT license (see LICENSE). + * + * + * Search arXiv via its HTTP API + * + * can search the following 1 or more fields: + * - author + * - title + * - abstract + * - journal reference + * - All fields + * journal's referenced, as well as all fields. + */ + + + +/** + * Searches arXiv for papers/documents that match the supplied parameters + * @param {string} all + * @param {string} author + * @param {string} title + * @param {string} abstrct + * @param {string} journal_ref + * @returns {Promise} + */ +function arxiv_search({all, author, title, abstrct, journal_ref}) { + var baseUrl = "http://export.arxiv.org/api/query?search_query="; + var first = true; + + if (author) { + if (!first) { + baseUrl += '+AND+'; + } + baseUrl += "au:" + author; + first = false; + } + + if (title) { + if (!first) { + baseUrl += '+AND+'; + } + baseUrl += "ti:" + title; + first = false; + } + + if (abstrct) { + if (!first) { + baseUrl += '+AND+'; + } + baseUrl += "abs:" + abstrct; + first = false; + } + + if (all) { + if (!first) { + baseUrl += '+AND+'; + } + baseUrl += "all:" + all; + } + + var deferred = $.Deferred(); + $.ajax({ + url: baseUrl, + type: "get", + dataType: "xml", + success: function(xml) { + var entry = []; + $(xml).find('entry').each(function (index) { + var id = $(this).find('id').text(); + var pub_date = $(this).find('published').text(); + var title = $(this).find('title').text(); + var summary = $(this).find('summary').text(); + var authors = []; + $(this).find('author').each(function (index) { + authors.push($(this).text()); + }); + + entry.push({'title': title, + 'link': id, + 'summary': summary, + 'date': pub_date, + 'authors': authors + }); + }); + + deferred.resolve(entry); + }, + error: function(status) { + console.log("request error " + status + " for url: "+baseUrl); + } + }); + return deferred.promise(); +} + + const arxivResults = [ { title: 'Example Paper Title 1', @@ -12,34 +108,4 @@ const arxivResults = [ abstract: 'This is the abstract of the second example paper.', link: 'https://arxiv.org/abs/example2' } - // ... more results ]; - -// 获取页面上的某个元素来展示搜索结果 -const resultsDiv = document.getElementById('arxiv-papers'); - -// 遍历搜索结果,并为每个结果创建一个展示元素 -arxivResults.forEach(result => { - const articleDiv = document.createElement('div'); - articleDiv.classList.add('article'); - - const title = document.createElement('h3'); - title.textContent = result.title; - articleDiv.appendChild(title); - - const authors = document.createElement('p'); - authors.textContent = `Authors: ${result.authors.join(', ')}`; - articleDiv.appendChild(authors); - - const abstract = document.createElement('p'); - abstract.textContent = `Abstract: ${result.abstract}`; - articleDiv.appendChild(abstract); - - const link = document.createElement('a'); - link.href = result.link; - link.textContent = 'View on arXiv'; - articleDiv.appendChild(link); - - // 将创建好的元素添加到页面上 - resultsDiv.appendChild(articleDiv); -}); \ No newline at end of file diff --git a/docs/zh/competition.md b/docs/zh/competition.md index 80b41ccaa..373337f6a 100644 --- a/docs/zh/competition.md +++ b/docs/zh/competition.md @@ -6,4 +6,4 @@ [CIKM 2024: AI辅助的先进空气动力学-优化汽车设计以实现最佳性能](https://competition.atomgit.com/competitionInfo?id=cda4e961b0c25858ca0fd2a4bdf87520),已进入评奖阶段。 -[IJCAI 2024: 任意三维几何外形车辆的风阻快速预测竞赛](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5),track A, B, C 代码:[paddle实现](https://github.com/PaddlePaddle/PaddleScience/tree/develop/jointContribution/IJCAI_2024) | [pytorch实现](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5)(点击**排行榜**可查看各个赛道前10名的代码) \ No newline at end of file +[IJCAI 2024: 任意三维几何外形车辆的风阻快速预测竞赛](https://competition.atomgit.com/competitionInfo?id=7f3f276465e9e845fd3a811d2d6925b5),track A, B, C 代码:[github仓库](https://github.com/PaddlePaddle/PaddleScience/tree/develop/jointContribution/IJCAI_2024) From dfed8ebc2d4a5b87c9e6f6e8bb0f6b0ae08760af Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Wed, 13 Nov 2024 13:31:27 +0800 Subject: [PATCH 03/10] bug fix --- docs/{index.md => arxiv.md} | 0 docs/javascripts/arxiv.js | 18 +----------------- mkdocs.yml | 2 +- 3 files changed, 2 insertions(+), 18 deletions(-) rename docs/{index.md => arxiv.md} (100%) diff --git a/docs/index.md b/docs/arxiv.md similarity index 100% rename from docs/index.md rename to docs/arxiv.md diff --git a/docs/javascripts/arxiv.js b/docs/javascripts/arxiv.js index 1dd72c893..377313fc7 100644 --- a/docs/javascripts/arxiv.js +++ b/docs/javascripts/arxiv.js @@ -26,7 +26,7 @@ * @returns {Promise} */ function arxiv_search({all, author, title, abstrct, journal_ref}) { - var baseUrl = "http://export.arxiv.org/api/query?search_query="; + var baseUrl = "https://export.arxiv.org/api/query?search_query="; var first = true; if (author) { @@ -93,19 +93,3 @@ function arxiv_search({all, author, title, abstrct, journal_ref}) { }); return deferred.promise(); } - - -const arxivResults = [ - { - title: 'Example Paper Title 1', - authors: ['Author1', 'Author2'], - abstract: 'This is the abstract of the first example paper.', - link: 'https://arxiv.org/abs/example1' - }, - { - title: 'Example Paper Title 2', - authors: ['Author3', 'Author4'], - abstract: 'This is the abstract of the second example paper.', - link: 'https://arxiv.org/abs/example2' - } -]; diff --git a/mkdocs.yml b/mkdocs.yml index 016e7c13e..2c8a570af 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -30,7 +30,7 @@ copyright: Copyright © 2022 - 2023 PaddlePaddle nav: - 科研工作站: - " ": - - 论文检索: index.md + - 论文检索: arxiv.md - Notebooks: zh/notebooks.md - 比赛: zh/competition.md - 课程: zh/tutorials.md From d4ea1d206c9e6772ea16309f3c05d1dce5ed11fc Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Wed, 13 Nov 2024 13:38:59 +0800 Subject: [PATCH 04/10] bug fix for index.md must exist --- docs/{arxiv.md => index.md} | 0 mkdocs.yml | 2 +- 2 files changed, 1 insertion(+), 1 deletion(-) rename docs/{arxiv.md => index.md} (100%) diff --git a/docs/arxiv.md b/docs/index.md similarity index 100% rename from docs/arxiv.md rename to docs/index.md diff --git a/mkdocs.yml b/mkdocs.yml index 2c8a570af..016e7c13e 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -30,7 +30,7 @@ copyright: Copyright © 2022 - 2023 PaddlePaddle nav: - 科研工作站: - " ": - - 论文检索: arxiv.md + - 论文检索: index.md - Notebooks: zh/notebooks.md - 比赛: zh/competition.md - 课程: zh/tutorials.md From 81b9b915b0a0b164bdca73477bac75feee2f77e1 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Mon, 18 Nov 2024 20:54:08 +0800 Subject: [PATCH 05/10] bug fix, add easy scholart --- docs/index.md | 55 ++++++++++++++++++++++++++++++++++---- docs/javascripts/arxiv.js | 38 +++++++++++++++++++++++++- docs/zh/fluid_mechanics.md | 19 +++++++------ 3 files changed, 96 insertions(+), 16 deletions(-) diff --git a/docs/index.md b/docs/index.md index 2886486df..950134f40 100644 --- a/docs/index.md +++ b/docs/index.md @@ -3,13 +3,58 @@ arXiv API Example + @@ -19,7 +64,7 @@
Title
- +

diff --git a/docs/javascripts/arxiv.js b/docs/javascripts/arxiv.js index 377313fc7..b7b0385a6 100644 --- a/docs/javascripts/arxiv.js +++ b/docs/javascripts/arxiv.js @@ -81,7 +81,8 @@ function arxiv_search({all, author, title, abstrct, journal_ref}) { 'link': id, 'summary': summary, 'date': pub_date, - 'authors': authors + 'authors': authors, + 'publicationName': "Computer Methods in Applied Mechanics and Engineering" }); }); @@ -93,3 +94,38 @@ function arxiv_search({all, author, title, abstrct, journal_ref}) { }); return deferred.promise(); } + + +// 调用 EasyScholar API 获取期刊排名信息的函数 +function getPublicationRank(publicationName) { + var url = 'https://www.easyscholar.cc/open/getPublicationRank?secretKey=f292c0ef1e3d40f2a54a826800f4032e&publicationName=' + encodeURIComponent(publicationName); + var deferred = $.Deferred(); + + $.ajax({ + url: url, + type: 'get', + dataType: 'json', // 假设API返回JSON格式数据 + success: function(response) { + if (response.code === 200 && response.msg === 'SUCCESS') { + var entry = { + 'data': response.data, + 'code': response.code, + 'msg': response.msg, + }; + console.log(response.data); + deferred.resolve(entry); + } else { + deferred.reject('Error: ' + response.msg); + } + }, + error: function(xhr, status, error) { + deferred.reject('AJAX Error: ' + error); + } + }); + return deferred.promise(); +} + +// 假设getStyledSpan函数已经定义,如下: +function getStyledSpan(text, backgroundColor) { + return `${text}`; + } \ No newline at end of file diff --git a/docs/zh/fluid_mechanics.md b/docs/zh/fluid_mechanics.md index 079540320..5dc029a1c 100644 --- a/docs/zh/fluid_mechanics.md +++ b/docs/zh/fluid_mechanics.md @@ -1,13 +1,12 @@ - -[科学计算案例:基于PaddleScience的Cylinder2D问题求解](https://aistudio.baidu.com/projectdetail/6178818?sUid=455441&shared=1&ts=1684397945680) - -[基于PaddleScience+CVit的advection方程求解](https://aistudio.baidu.com/projectdetail/8141430) - -[共创计划:基于 PINN 方法求解可压缩流体欧拉方程组的正问题](https://aistudio.baidu.com/projectdetail/7593837) - -[拉格朗日粒子流体Benchmark开源数据集](https://aistudio.baidu.com/projectdetail/7507477) - -[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7309026) +|年份 | 期刊 | 论文PDF | 问题类型 | 在线运行 | 网络/算法类型 | 神经网络/传统算法 | +|-----|-----|-----|---------|-----|---------|----| +|2022|Neural Networks| [Transformers for Modeling Physical Systems](https://arxiv.org/pdf/2010.03957?) | 2D低雷诺数瞬态流动问题 | [Cylinder2D问题求解](https://aistudio.baidu.com/projectdetail/6178818?sUid=455441&shared=1&ts=1684397945680) | 物理嵌入 | PINN | 监督学习 | +|2024|arXiv|[CVIT: CONTINUOUS VISION TRANSFORMER FOR OPERATOR LEARNING](https://arxiv.org/pdf/2405.13998)|1D对流advection方程求解|[CVit的advection方程求解](https://aistudio.baidu.com/projectdetail/8141430)|神经算子|CViT, Vision Transformer| +|2024|Journal of Scientific Computing|[Discontinuity Computing Using Physics-Informed Neural Network](https://arxiv.org/pdf/2206.03864)|1D欧拉方程,lax激波管,sod激波管。2D欧拉方程|[PINN求解可压缩流体欧拉方程组的正问题](https://aistudio.baidu.com/projectdetail/8141430)|神经算子|PINN| +|-|-|-|3D瞬态lagrange物质点法|[拉格朗日粒子流体Benchmark开源数据集](https://aistudio.baidu.com/projectdetail/7507477)|传统CFD|MPM DEM SPH| +|-|-|-|1D wave方程, 2D NS方程|[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7507477)|神经算子|PITT,Transformer| + +##待更新 [DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/5489960?channelType=0&channel=0) From 2df98546188f7e6f144e45590c9003d9cca1b4c1 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Mon, 18 Nov 2024 21:03:07 +0800 Subject: [PATCH 06/10] readthedocs fail --- docs/javascripts/arxiv.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/javascripts/arxiv.js b/docs/javascripts/arxiv.js index b7b0385a6..9648c8530 100644 --- a/docs/javascripts/arxiv.js +++ b/docs/javascripts/arxiv.js @@ -128,4 +128,4 @@ function getPublicationRank(publicationName) { // 假设getStyledSpan函数已经定义,如下: function getStyledSpan(text, backgroundColor) { return `${text}`; - } \ No newline at end of file + } From a0fa77615c453cf05fb62c89074a52e395b149e0 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Tue, 19 Nov 2024 10:48:39 +0800 Subject: [PATCH 07/10] AI CT image --- docs/zh/biology_medicine.md | 16 ++++++++++++++++ docs/zh/fluid_mechanics.md | 2 +- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/docs/zh/biology_medicine.md b/docs/zh/biology_medicine.md index b8c5a9c68..1820f3493 100644 --- a/docs/zh/biology_medicine.md +++ b/docs/zh/biology_medicine.md @@ -1,3 +1,16 @@ + +|年份 | 期刊 | 论文PDF | 问题类型 | 在线运行 | 网络/算法类型 | 神经网络/传统算法 | +|-----|-----|-----|---------|-----|---------|----| +|-----|-----|-----|AI 医疗影像|[CheXNet-CAM:CT 影像肺炎检测可视化](https://aistudio.baidu.com/projectdetail/2535474)|---------|----| +|-----|-----|-----|AI 医疗影像|[基于Unet+++实现脊柱MRI定位(上)](https://aistudio.baidu.com/projectdetail/2354135)|---------|----| +|-----|-----|-----|AI 医疗影像|[基于Unet+++实现脊柱MRI定位(中)](https://aistudio.baidu.com/projectdetail/4646398)|---------|----| +|-----|-----|-----|AI 医疗影像|[医学图像处理工具SimpleITK与DataSet](https://aistudio.baidu.com/projectdetail/1915947)|---------|----| +|-----|-----|-----|AI 医疗影像|[基于3D-Unet的脑肿瘤MRI图像分割](https://aistudio.baidu.com/projectdetail/388306)|---------|----| +|-----|-----|-----|AI 医疗影像|[医学影像挑战赛(分类)](https://aistudio.baidu.com/projectdetail/1993210)|---------|----| +|-----|-----|-----|AI 医疗影像|[肝脏CT影像分割](https://aistudio.baidu.com/projectdetail/6212016)|---------|----| + + + [【PaddleHelix】螺旋桨生物计算开源工具集](https://aistudio.baidu.com/aistudio/projectdetail/1293361?channelType=0&channel=0&sUid=14197935&ts=1731058781419) [使用螺旋桨PaddleHelix完成RNA结构预测竞赛的前置基础知识整理](https://aistudio.baidu.com/aistudio/projectdetail/1404818?channelType=0&channel=0&sUid=14197935&ts=1731058794651) @@ -39,3 +52,6 @@ [医学影像数据集集锦](https://aistudio.baidu.com/aistudio/projectdetail/462184?channelType=0&channel=0&sUid=14197935&ts=1731060976805) [基于紫外差分吸收光谱技术与神经网络结合的呼出气体中氨气的检测](https://aistudio.baidu.com/aistudio/projectdetail/8190914?channelType=0&channel=0&sUid=14197935&ts=1731058813858) + + + diff --git a/docs/zh/fluid_mechanics.md b/docs/zh/fluid_mechanics.md index 5dc029a1c..722ab59ed 100644 --- a/docs/zh/fluid_mechanics.md +++ b/docs/zh/fluid_mechanics.md @@ -6,7 +6,7 @@ |-|-|-|3D瞬态lagrange物质点法|[拉格朗日粒子流体Benchmark开源数据集](https://aistudio.baidu.com/projectdetail/7507477)|传统CFD|MPM DEM SPH| |-|-|-|1D wave方程, 2D NS方程|[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7507477)|神经算子|PITT,Transformer| -##待更新 +## 待整理 [DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/5489960?channelType=0&channel=0) From 549cc05c7d95f8a4acf81d27eddd00053953fa32 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Tue, 19 Nov 2024 10:55:42 +0800 Subject: [PATCH 08/10] fix --- docs/zh/biology_medicine.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/zh/biology_medicine.md b/docs/zh/biology_medicine.md index 1820f3493..ed9554b4b 100644 --- a/docs/zh/biology_medicine.md +++ b/docs/zh/biology_medicine.md @@ -10,6 +10,7 @@ |-----|-----|-----|AI 医疗影像|[肝脏CT影像分割](https://aistudio.baidu.com/projectdetail/6212016)|---------|----| +## 待整理 [【PaddleHelix】螺旋桨生物计算开源工具集](https://aistudio.baidu.com/aistudio/projectdetail/1293361?channelType=0&channel=0&sUid=14197935&ts=1731058781419) From 57a54e97bad77c3a8edfd0f43e4d324fbe990a54 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Tue, 19 Nov 2024 14:51:31 +0800 Subject: [PATCH 09/10] fix --- docs/zh/biology_medicine.md | 4 ++++ docs/zh/fluid_mechanics.md | 6 ++---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/docs/zh/biology_medicine.md b/docs/zh/biology_medicine.md index ed9554b4b..4c1e12fd5 100644 --- a/docs/zh/biology_medicine.md +++ b/docs/zh/biology_medicine.md @@ -8,6 +8,10 @@ |-----|-----|-----|AI 医疗影像|[基于3D-Unet的脑肿瘤MRI图像分割](https://aistudio.baidu.com/projectdetail/388306)|---------|----| |-----|-----|-----|AI 医疗影像|[医学影像挑战赛(分类)](https://aistudio.baidu.com/projectdetail/1993210)|---------|----| |-----|-----|-----|AI 医疗影像|[肝脏CT影像分割](https://aistudio.baidu.com/projectdetail/6212016)|---------|----| +|-----|-----|-----|AI 医疗影像|[利用胸部CT和PaddleSeg计算心胸比](https://aistudio.baidu.com/projectdetail/1438719)|---------|----| + + + ## 待整理 diff --git a/docs/zh/fluid_mechanics.md b/docs/zh/fluid_mechanics.md index 722ab59ed..b8b87b68e 100644 --- a/docs/zh/fluid_mechanics.md +++ b/docs/zh/fluid_mechanics.md @@ -5,13 +5,11 @@ |2024|Journal of Scientific Computing|[Discontinuity Computing Using Physics-Informed Neural Network](https://arxiv.org/pdf/2206.03864)|1D欧拉方程,lax激波管,sod激波管。2D欧拉方程|[PINN求解可压缩流体欧拉方程组的正问题](https://aistudio.baidu.com/projectdetail/8141430)|神经算子|PINN| |-|-|-|3D瞬态lagrange物质点法|[拉格朗日粒子流体Benchmark开源数据集](https://aistudio.baidu.com/projectdetail/7507477)|传统CFD|MPM DEM SPH| |-|-|-|1D wave方程, 2D NS方程|[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7507477)|神经算子|PITT,Transformer| +|2021|SIAM Review|[DeepXDE: A deep learning library for solving differential equations](https://arxiv.org/pdf/1907.04502)|2D 瞬态固体传热, 2D NS方程|[DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/7507477)|物理嵌入|PINN| +|2022|Connection Science|[AMGNET: multi-scale graph neural networks for flow field prediction](https://www.tandfonline.com/doi/pdf/10.1080/09540091.2022.2131737)|2D 稳态圆柱Re=78, 2D 稳态机翼Ma=0.65|[AMGNET 论文复现](https://aistudio.baidu.com/projectdetail/5592458)|神经算子|AMGNET| ## 待整理 -[DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/5489960?channelType=0&channel=0) - -[AI for Science 共创计划 AMGNET 论文复现](https://aistudio.baidu.com/projectdetail/5592458?channelType=0&channel=0) - [AI for Science 共创计划GNN Laminar Flow 论文复现](https://aistudio.baidu.com/projectdetail/5563934?channelType=0&channel=0) [共创计划:基于Transformer架构的流体流动降阶模拟的研究](https://aistudio.baidu.com/projectdetail/7509905) From 2133a2e1e768edae0ec1f109bb60a73cba2cd241 Mon Sep 17 00:00:00 2001 From: wanggaun1995 <772359200@qq.com> Date: Thu, 21 Nov 2024 16:27:31 +0800 Subject: [PATCH 10/10] "fix" --- docs/zh/chemistry_material_science.md | 4 ++++ docs/zh/cooperation.md | 14 +++++++++++--- docs/zh/fluid_mechanics.md | 8 +++----- 3 files changed, 18 insertions(+), 8 deletions(-) diff --git a/docs/zh/chemistry_material_science.md b/docs/zh/chemistry_material_science.md index 6dd9080c3..c43b554f4 100644 --- a/docs/zh/chemistry_material_science.md +++ b/docs/zh/chemistry_material_science.md @@ -1,3 +1,7 @@ +|年份 | 期刊 | 论文PDF | 问题类型 | 在线运行 | 网络/算法类型 | 神经网络/传统算法 | +|-----|-----|-----|---------|-----|---------|----| +|2018|Physics Review Letter|[Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties](https://arxiv.org/pdf/1710.10324)|材料属性预测|[CGCNN 可解释预测材料属性的晶体图卷积神经网络](https://aistudio.baidu.com/projectdetail/8560880)|---------|----| + [材料缺陷检测](https://aistudio.baidu.com/aistudio/projectdetail/3482461?channelType=0&channel=0&sUid=14197935&ts=1731059563182) [使用Paddle框架实现晶圆缺陷图片相似度推荐](https://aistudio.baidu.com/aistudio/projectdetail/5818368?channelType=0&channel=0&sUid=14197935&ts=1731059764951) diff --git a/docs/zh/cooperation.md b/docs/zh/cooperation.md index 9f34244ca..9f255ea0d 100644 --- a/docs/zh/cooperation.md +++ b/docs/zh/cooperation.md @@ -1,8 +1,16 @@ -# 共创计划 +# 共创计划2期 -PaddleScience 作为一个开源项目,欢迎来各行各业的伙伴携手共建基于飞桨的 AI for Science 领域顶尖开源项目,打造活跃的前瞻性的 AI for Science 开源社区,建立产学研闭环,推动科研创新与产业赋能。点击了解 [飞桨 AI for Science 共创计划](https://www.paddlepaddle.org.cn/science) -## 项目精选 +🔥 [AI for Science 热身任务:CGCNN 可解释预测材料属性的晶体图卷积神经网络](https://aistudio.baidu.com/projectdetail/8560880),打卡领取GPU算力 + +🔥 [AI for Science 热身任务:PaddleScience PINN 板壳线弹性静力学分析](https://aistudio.baidu.com/projectdetail/8556958),打卡领取GPU算力 + +🔥 [飞桨AI for Science前沿讲座系列课程 & 代码入门与实操课程进行中 ](https://mp.weixin.qq.com/s/n-vGnGM9di_3IByTC56hUw),清华、北大、中科院等高校机构知名学者分享前沿研究成果,火热报名中。 + + +PaddleScience 作为一个开源项目,欢迎来各行各业的伙伴携手共建基于飞桨的 AI for Science 领域顶尖开源项目,打造活跃的前瞻性的 AI for Science 开源社区,建立产学研闭环,推动科研创新与产业赋能。点击了解 [飞桨 AI for Science 共创计划](https://aistudio.baidu.com/activitydetail/1502019365) + +## 共创计划1期,项目精选 - 使用嵌套傅立叶神经算子进行实时高分辨二氧化碳地质封存预测: - 多源异构数据与机理融合的极端天气预报算法研究: diff --git a/docs/zh/fluid_mechanics.md b/docs/zh/fluid_mechanics.md index b8b87b68e..ecc03a19a 100644 --- a/docs/zh/fluid_mechanics.md +++ b/docs/zh/fluid_mechanics.md @@ -7,14 +7,12 @@ |-|-|-|1D wave方程, 2D NS方程|[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7507477)|神经算子|PITT,Transformer| |2021|SIAM Review|[DeepXDE: A deep learning library for solving differential equations](https://arxiv.org/pdf/1907.04502)|2D 瞬态固体传热, 2D NS方程|[DeepXDE传热和流体科学计算案例](https://aistudio.baidu.com/projectdetail/7507477)|物理嵌入|PINN| |2022|Connection Science|[AMGNET: multi-scale graph neural networks for flow field prediction](https://www.tandfonline.com/doi/pdf/10.1080/09540091.2022.2131737)|2D 稳态圆柱Re=78, 2D 稳态机翼Ma=0.65|[AMGNET 论文复现](https://aistudio.baidu.com/projectdetail/5592458)|神经算子|AMGNET| +|2021|Physics of Fluids|[Graph neural networks for laminar flow prediction around random 2D shapes](https://arxiv.org/pdf/2107.11529)|2D 稳态圆柱|[GNN Laminar Flow 论文复现](https://aistudio.baidu.com/projectdetail/5563934)|神经算子|图卷积神经网络| +|-|-|-|2D 气液两相流动|[基于Transformer的神经算子预测模型](https://aistudio.baidu.com/projectdetail/7509905)|模型降阶|ROMER| +|2021|Journal of Fluid Mechanics|[Unsupervised deep learning for super-resolution reconstruction of turbulence](https://arxiv.org/pdf/2007.15324)|JHTDB Re=1000 强迫各向异性瞬态湍流|[CycleGAN 湍流超分辨率重建](https://aistudio.baidu.com/projectdetail/4493261)|流场重建|对抗神经网络 Cycle-GAN| ## 待整理 -[AI for Science 共创计划GNN Laminar Flow 论文复现](https://aistudio.baidu.com/projectdetail/5563934?channelType=0&channel=0) - -[共创计划:基于Transformer架构的流体流动降阶模拟的研究](https://aistudio.baidu.com/projectdetail/7509905) - -[[论文复现赛第七期] 54 - CycleGAN 湍流超分辨率重建](https://aistudio.baidu.com/projectdetail/4493261?channelType=0&channel=0) [【论文复现】基于神经微分方程的流体降阶模型(超详细讲解Neural ODE)](https://aistudio.baidu.com/projectdetail/5680422?searchKeyword=%E8%B6%85%E8%AF%A6%E7%BB%86%E8%AE%B2%E8%A7%A3ODE&searchTab=ALL)