From 6040830558031f62ebf9a147c247fe0456d9fbac Mon Sep 17 00:00:00 2001 From: HydrogenSulfate <490868991@qq.com> Date: Tue, 14 Nov 2023 15:59:00 +0800 Subject: [PATCH] [Doc] Add pretrained model for cylinder2d_unsteady_Re100, darcy2d and fix filename (#638) * update pretrained model dowload link * update pretrain model and metric for cylinder2d_unsteady * update pretrained model for darcy2d example and fix pretrainde model filename --- docs/zh/examples/cylinder2d_unsteady.md | 16 ++++++++++++++++ docs/zh/examples/darcy2d.md | 5 +++++ docs/zh/examples/ldc2d_steady.md | 4 ++-- docs/zh/examples/ldc2d_unsteady.md | 4 ++-- docs/zh/user_guide.md | 2 +- 5 files changed, 26 insertions(+), 5 deletions(-) diff --git a/docs/zh/examples/cylinder2d_unsteady.md b/docs/zh/examples/cylinder2d_unsteady.md index 7ee28332d..300f483d1 100644 --- a/docs/zh/examples/cylinder2d_unsteady.md +++ b/docs/zh/examples/cylinder2d_unsteady.md @@ -14,6 +14,22 @@ python cylinder2d_unsteady_Re100.py ``` +=== "模型评估命令" + + ``` sh + # linux + wget https://paddle-org.bj.bcebos.com/paddlescience/datasets/cylinder2d_unsteady_Re100/cylinder2d_unsteady_Re100_dataset.tar + # windows + # curl https://paddle-org.bj.bcebos.com/paddlescience/datasets/cylinder2d_unsteady_Re100/cylinder2d_unsteady_Re100_dataset.tar --output cylinder2d_unsteady_Re100_dataset.tar + # unzip it + tar -xvf cylinder2d_unsteady_Re100_dataset.tar + python cylinder2d_unsteady_Re100.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/cylinder2d_unsteady_Re100/cylinder2d_unsteady_Re100_pretrained.pdparams + ``` + +| 预训练模型 | 指标 | +|:--| :--| +| [cylinder2d_unsteady_Re100_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/cylinder2d_unsteady_Re100/cylinder2d_unsteady_Re100_pretrained.pdparams) | loss(Residual): 0.00398
MSE.continuity(Residual): 0.00126
MSE.momentum_x(Residual): 0.00151
MSE.momentum_y(Residual): 0.00120 | + ## 1. 背景简介 圆柱绕流问题可以应用于很多领域。例如，在工业设计中，它可以被用来模拟和优化流体在各种设备中的流动，如风力发电机、汽车和飞机的流体动力学性能等。在环保领域，圆柱绕流问题也有应用，如预测和控制河流的洪水、研究污染物的扩散等。此外，在工程实践中，如流体动力学、流体静力学、热交换、空气动力学等领域，圆柱绕流问题也具有实际意义。 diff --git a/docs/zh/examples/darcy2d.md b/docs/zh/examples/darcy2d.md index 681a1e669..c5d57aceb 100644 --- a/docs/zh/examples/darcy2d.md +++ b/docs/zh/examples/darcy2d.md @@ -14,6 +14,11 @@ python darcy2d.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/darcy2d/darcy2d_pretrained.pdparams ``` +| 预训练模型 | 指标 | +|:--| :--| +| [darcy2d_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/darcy2d/darcy2d_pretrained.pdparams) | loss(Residual): 0.36500
MSE.poisson(Residual): 0.00006 | + + ## 1. 背景简介 Darcy Flow是一个基于达西定律的工具，用于计算液体的流动。在地下水模拟、水文学、水文地质学和石油工程等领域中，Darcy Flow被广泛应用。 diff --git a/docs/zh/examples/ldc2d_steady.md b/docs/zh/examples/ldc2d_steady.md index d9d2de8f7..037dc50bc 100644 --- a/docs/zh/examples/ldc2d_steady.md +++ b/docs/zh/examples/ldc2d_steady.md @@ -11,12 +11,12 @@ === "模型评估命令" ``` sh - python ldc2d_steady_Re10.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_steady_Re10/ldc2d_steady_Re10_pretrain.pdparams + python ldc2d_steady_Re10.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_steady_Re10/ldc2d_steady_Re10_pretrained.pdparams ``` | 预训练模型 | 指标 | |:--| :--| -| [ldc2d_steady_Re10_pretrain.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_steady_Re10/ldc2d_steady_Re10_pretrain.pdparams) | loss(Residual): 365.36164
MSE.momentum_x(Residual): 0.01435
MSE.continuity(Residual): 0.04072
MSE.momentum_y(Residual): 0.02471 | +| [ldc2d_steady_Re10_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_steady_Re10/ldc2d_steady_Re10_pretrained.pdparams) | loss(Residual): 365.36164
MSE.momentum_x(Residual): 0.01435
MSE.continuity(Residual): 0.04072
MSE.momentum_y(Residual): 0.02471 | ## 1. 背景简介 diff --git a/docs/zh/examples/ldc2d_unsteady.md b/docs/zh/examples/ldc2d_unsteady.md index c919fda93..869836229 100644 --- a/docs/zh/examples/ldc2d_unsteady.md +++ b/docs/zh/examples/ldc2d_unsteady.md @@ -11,12 +11,12 @@ === "模型评估命令" ``` sh - python ldc2d_unsteady_Re10.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_unsteady_Re10/ldc2d_unsteady_Re10_pretrain.pdparams + python ldc2d_unsteady_Re10.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_unsteady_Re10/ldc2d_unsteady_Re10_pretrained.pdparams ``` | 预训练模型 | 指标 | |:--| :--| -| [ldc2d_unsteady_Re10_pretrain.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_unsteady_Re10/ldc2d_unsteady_Re10_pretrain.pdparams) | loss(Residual): 155652.67530
MSE.momentum_x(Residual): 6.78030
MSE.continuity(Residual): 0.16590
MSE.momentum_y(Residual): 12.05981 | +| [ldc2d_unsteady_Re10_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/ldc2d_unsteady_Re10/ldc2d_unsteady_Re10_pretrained.pdparams) | loss(Residual): 155652.67530
MSE.momentum_x(Residual): 6.78030
MSE.continuity(Residual): 0.16590
MSE.momentum_y(Residual): 12.05981 | ## 1. 背景简介 diff --git a/docs/zh/user_guide.md b/docs/zh/user_guide.md index 9816f8b52..d699199e6 100644 --- a/docs/zh/user_guide.md +++ b/docs/zh/user_guide.md @@ -179,7 +179,7 @@ PaddleScience/examples/bracket/outputs_bracket/ # 用该模型及其对应的预训练模型路径(或下载地址 url)两个参数初始化 solver solver = ppsci.solver.Solver( model=model, - pretrained_model_path="/path/to/pretrain.pdparams", + pretrained_model_path="/path/to/pretrained.pdparams", ) # 在 Solver(...) 中会自动从给定的 pretrained_model_path 加载(下载)参数并赋值给 model 的对应参数 ```