[Doc] Add pretrained model for laplace2d & refine comments (#639)

HydrogenSulfate · web-flow · commit a14d6bd7d09e · 2023-11-15T11:07:22.000+08:00
* update laplace2d pretrained model

* remove 'after finished training' comment in evaluate function

* update README.md
diff --git a/README.md b/README.md
@@ -25,45 +25,45 @@ PaddleScience 是一个基于深度学习框架 PaddlePaddle 开发的科学计
 
 | 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 |
 |-----|---------|-----|---------|----|---------|---------|
-| 微分方程 | [拉普拉斯方程](./docs/zh/examples/laplace2d.md) | 机理驱动 | MLP | 无监督学习 | -        | - |
-| 微分方程 | [伯格斯方程](./docs/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) |</center>
-| 微分方程 | [非线性偏微分方程](./docs/zh/examples/pirbn.md) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://arxiv.org/abs/2304.06234) |
-| 微分方程 | [洛伦兹方程](./docs/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](./docs/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](./docs/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 | [拉普拉斯方程](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/laplace2d) | 机理驱动 | MLP | 无监督学习 | -        | - |
+| 微分方程 | [伯格斯方程](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/deephpms) | 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) |</center>
+| 微分方程 | [非线性偏微分方程](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/pirbn) | 机理驱动 | MLP | 无监督学习 | - | [Paper](https://arxiv.org/abs/2304.06234) |
+| 微分方程 | [洛伦兹方程](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/lorenz) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/rossler) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/deeponet) | 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<sup>coming soon</sup> | 机理驱动 | gPINN | 半监督学习 | - |  [Paper](https://www.sciencedirect.com/science/article/abs/pii/S0045782522001438?via%3Dihub) |
-| 积分方程 | [沃尔泰拉积分方程](./docs/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) |
+| 积分方程 | [沃尔泰拉积分方程](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/volterra_ide) | 机理驱动 | MLP | 无监督学习 | - | [Project](https://github.com/lululxvi/deepxde/blob/master/examples/pinn_forward/Volterra_IDE.py) |
 
 <br>
 <p align="center"><b>技术科学(AI for Technology)</b></p>
 
 | 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 |
 |-----|---------|-----|---------|----|---------|---------|
-| 定常不可压流体 | [2D 定常方腔流](./docs/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](./docs/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](./docs/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 血管瘤](./docs/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](./docs/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](./docs/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](./docs/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](./docs/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](./docs/zh/examples/shock_wave.md) | 机理驱动 | PINN-WE | 无监督学习 | - | [Paper](https://arxiv.org/abs/2206.03864)|
+| 定常不可压流体 | [2D 定常方腔流](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/ldc2d_steady) | 机理驱动 | MLP | 无监督学习 | - |  |
+| 定常不可压流体 | [2D 达西流](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/darcy2d) | 机理驱动 | MLP | 无监督学习 | - |   |
+| 定常不可压流体 | [2D 管道流](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/labelfree_DNN_surrogate) | 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 血管瘤](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/aneurysm) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/deepcfd) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/ldc2d_unsteady) | 机理驱动 | MLP | 无监督学习 | - | - |
+| 非定常不可压流体 | [Re100 2D 圆柱绕流](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/cylinder2d_unsteady) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/cylinder2d_unsteady_transformer_physx) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/shock_wave) | 机理驱动 | PINN-WE | 无监督学习 | - | [Paper](https://arxiv.org/abs/2206.03864)|
 | 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) |
-| 流固耦合 | [涡激振动](./docs/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](./docs/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)|
+| 流固耦合 | [涡激振动](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/viv) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/bubble) | 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)|
 | 多相流 | 非高斯渗透率场估计<sup>coming soon</sup> | 机理驱动 | cINN | 监督学习 | - | [Paper](https://pubs.aip.org/aip/adv/article/12/3/035153/2819394/Predicting-micro-bubble-dynamics-with-semi-physics)|
-| 流场高分辨率重构 | [2D 湍流流场重构](./docs/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)<br>[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://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/tempoGAN) | 数据驱动 | tempoGAN | 监督学习 | [Train Data](https://paddle-org.bj.bcebos.com/paddlescience/datasets/tempoGAN/2d_train.mat)<br>[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)<br>[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)<br>[Data2](https://drive.google.com/drive/folders/1pVW4epkeHkT2WHZB7Dym5IURcfOP4cXu)<br>[Data3](https://drive.google.com/drive/folders/1xIY_jIu-hNcRY-TTf4oYX1Xg4_fx8ZvD) | [Paper](https://arxiv.org/pdf/2202.11214.pdf) |
 | 流场高分辨率重构 | 基于扩散的流体超分重构<sup>coming soon</sup> | 数理融合 | DDPM | 监督学习 | - | [Paper](https://www.sciencedirect.com/science/article/pii/S0021999123000670)|
-| 求解器耦合 | [CFD-GCN](./docs/zh/examples/cfdgcn.md) | 数据驱动 | GCN | 监督学习 | [Data](https://aistudio.baidu.com/aistudio/datasetdetail/184778)<br>[Mesh](https://paddle-org.bj.bcebos.com/paddlescience/datasets/CFDGCN/meshes.tar) | [Paper](https://arxiv.org/abs/2007.04439)|
+| 求解器耦合 | [CFD-GCN](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/cfdgcn) | 数据驱动 | GCN | 监督学习 | [Data](https://aistudio.baidu.com/aistudio/datasetdetail/184778)<br>[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](https://github.com/PaddlePaddle/PaddleScience/blob/develop/examples/euler_beam/euler_beam.py) | 机理驱动 | MLP | 无监督学习 | - | - |
 | 受力分析 | [2D 平板变形](https://aistudio.baidu.com/aistudio/projectdetail/5792325) | 机理驱动 | MLP | 无监督学习 | - | - |
-| 受力分析 | [3D 连接件变形](./docs/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](./docs/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 | [3D 连接件变形](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/bracket) | 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](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/phylstm) | 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) |
 
 <br>
 <p align="center"><b>材料科学(AI for Material)</b></p>
@@ -78,7 +78,7 @@ PaddleScience 是一个基于深度学习框架 PaddlePaddle 开发的科学计
 
 | 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 | [FourCastNet 气象预报](./docs/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 | [FourCastNet 气象预报](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/fourcastnet) | 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 | GraphCast 气象预报<sup>coming soon</sup> | 数据驱动 | GraphCastNet* | 监督学习 | - | [Paper](https://arxiv.org/pdf/2202.11214.pdf) |
 | 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) | - |
 
diff --git a/docs/zh/examples/laplace2d.md b/docs/zh/examples/laplace2d.md
@@ -8,6 +8,16 @@
     python laplace2d.py
     ```
 
+=== "模型评估命令"
+
+    ``` sh
+    python laplace2d.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/laplace2d/laplace2d_pretrained.pdparams
+    ```
+
+| 预训练模型  | 指标 |
+|:--| :--|
+| [laplace2d_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/laplace2d/laplace2d_pretrained.pdparams) | loss(MSE_Metric): 0.00002<br>MSE.u(MSE_Metric): 0.00002 |
+
 ## 1. 背景简介
 
 拉普拉斯方程由法国数学家拉普拉斯首先提出而得名，该方程在许多领域都有重要应用，例如电磁学、天文学和流体力学等。在实际应用中，拉普拉斯方程的求解往往是一个复杂的数学问题。对于一些具有特定边界条件和初始条件的实际问题，可以通过特定的数值方法（如有限元方法、有限差分方法等）来求解拉普拉斯方程。对于一些复杂的问题，可能需要采用更高级的数值方法或者借助高性能计算机进行计算。
diff --git a/examples/bracket/bracket.py b/examples/bracket/bracket.py
@@ -521,9 +521,9 @@ def evaluate(cfg: DictConfig):
         pretrained_model_path=cfg.EVAL.pretrained_model_path,
         eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
     )
-    # evaluate after finished training
+    # evaluate
     solver.eval()
-    # visualize prediction after finished training
+    # visualize prediction
     solver.visualize()
 
 
diff --git a/examples/bubble/bubble.py b/examples/bubble/bubble.py
@@ -356,7 +356,7 @@ def transform_out(in_, out):
     )
     solver.eval()
 
-    # visualize prediction after finished training
+    # visualize prediction
     visu_mat = geom["time_rect_visu"].sample_interior(
         NPOINT_PDE * NTIME_PDE, evenly=True
     )
diff --git a/examples/deepcfd/deepcfd.py b/examples/deepcfd/deepcfd.py
@@ -446,7 +446,7 @@ def metric_expr(
     PLOT_DIR = os.path.join(cfg.output_dir, "visual")
     os.makedirs(PLOT_DIR, exist_ok=True)
 
-    # visualize prediction after finished training
+    # visualize prediction
     predict_and_save_plot(test_x, test_y, 0, solver, PLOT_DIR)
 
 
diff --git a/examples/epnn/epnn.py b/examples/epnn/epnn.py
@@ -187,7 +187,7 @@ def transform_f_stress(_in):
         pretrained_model_path=cfg.EVAL.pretrained_model_path,
         eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
     )
-    # evaluate after finished training
+    # evaluate
     solver.eval()
 
 
diff --git a/examples/hpinns/holography.py b/examples/hpinns/holography.py
@@ -271,7 +271,7 @@ def train(cfg: DictConfig):
 
             # train model
             solver.train()
-            # evaluate after finished training
+            # evaluate
             solver.eval()
             # append objective loss for plot
             loss_log_obj.append(func_module.loss_obj)
@@ -405,7 +405,7 @@ def evaluate(cfg: DictConfig):
         pretrained_model_path=cfg.EVAL.pretrained_model_path,
     )
 
-    # evaluate after finished training
+    # evaluate
     solver.eval()
 
 
diff --git a/examples/laplace/laplace2d.py b/examples/laplace/laplace2d.py
@@ -201,7 +201,7 @@ def u_solution_func(out):
         pretrained_model_path=cfg.EVAL.pretrained_model_path,
     )
     solver.eval()
-    # visualize prediction after finished training
+    # visualize prediction
     solver.visualize()
 
 
diff --git a/examples/phylstm/phylstm2.py b/examples/phylstm/phylstm2.py
@@ -302,7 +302,7 @@ def evaluate(cfg: DictConfig):
         pretrained_model_path=cfg.EVAL.pretrained_model_path,
         eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
     )
-    # evaluate after finished training
+    # evaluate
     solver.eval()
 
 
diff --git a/examples/phylstm/phylstm3.py b/examples/phylstm/phylstm3.py
@@ -321,7 +321,7 @@ def evaluate(cfg: DictConfig):
         eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
     )
 
-    # evaluate after finished training
+    # evaluate
     solver.eval()
 
 

Original file line number	Diff line number	Diff line change
`@@ -356,7 +356,7 @@ def transform_out(in_, out):`
`356`	`356`	`)`
`357`	`357`	`solver.eval()`
`358`	`358`
`359`		`- # visualize prediction after finished training`
	`359`	`+ # visualize prediction`
`360`	`360`	`visu_mat = geom["time_rect_visu"].sample_interior(`
`361`	`361`	`NPOINT_PDE * NTIME_PDE, evenly=True`
`362`	`362`	`)`
Original file line number	Diff line number	Diff line change
`@@ -187,7 +187,7 @@ def transform_f_stress(_in):`
`187`	`187`	`pretrained_model_path=cfg.EVAL.pretrained_model_path,`
`188`	`188`	`eval_with_no_grad=cfg.EVAL.eval_with_no_grad,`
`189`	`189`	`)`
`190`		`- # evaluate after finished training`
	`190`	`+ # evaluate`
`191`	`191`	`solver.eval()`
`192`	`192`
`193`	`193`
Original file line number	Diff line number	Diff line change
`@@ -201,7 +201,7 @@ def u_solution_func(out):`
`201`	`201`	`pretrained_model_path=cfg.EVAL.pretrained_model_path,`
`202`	`202`	`)`
`203`	`203`	`solver.eval()`
`204`		`- # visualize prediction after finished training`
	`204`	`+ # visualize prediction`
`205`	`205`	`solver.visualize()`
`206`	`206`
`207`	`207`
Original file line number	Diff line number	Diff line change
`@@ -302,7 +302,7 @@ def evaluate(cfg: DictConfig):`
`302`	`302`	`pretrained_model_path=cfg.EVAL.pretrained_model_path,`
`303`	`303`	`eval_with_no_grad=cfg.EVAL.eval_with_no_grad,`
`304`	`304`	`)`
`305`		`- # evaluate after finished training`
	`305`	`+ # evaluate`
`306`	`306`	`solver.eval()`
`307`	`307`
`308`	`308`
Original file line number	Diff line number	Diff line change
`@@ -321,7 +321,7 @@ def evaluate(cfg: DictConfig):`
`321`	`321`	`eval_with_no_grad=cfg.EVAL.eval_with_no_grad,`
`322`	`322`	`)`
`323`	`323`
`324`		`- # evaluate after finished training`
	`324`	`+ # evaluate`
`325`	`325`	`solver.eval()`
`326`	`326`
`327`	`327`