PaddlePaddle · zhiminzhang0830 · Jul 10, 2024 · Jun 19, 2024 · Jun 19, 2024 · Jun 19, 2024
diff --git a/README.md b/README.md
@@ -46,7 +46,9 @@ 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 |
 |-----|---------|-----|---------|----|---------|---------|
-| 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 | - |  |
+| 一维线性对流问题 | [1D 线性对流](https://paddlescience-docs.readthedocs.io/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](https://paddlescience-docs.readthedocs.io/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](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)|
@@ -102,6 +104,7 @@ PaddleScience 是一个基于深度学习框架 PaddlePaddle 开发的科学计
 <!-- --8<-- [start:update] -->
 ## 🕘最近更新
 
+- 添加 CVit(基于 Advection 方程和 N-S 方程求解) [CVit(Navier-Stokes)](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/ns_cvit/)、[CVit(Advection)](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/adv_cvit/)。
 - 添加 PirateNet(基于 Allen-cahn 方程和 N-S 方程求解) [Allen-Cahn](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/allen_cahn/)、[LDC2D(Re3200)](https://paddlescience-docs.readthedocs.io/zh/latest/zh/examples/ldc2d_steady/)。
 - 基于 PaddleScience 的快速热仿真方法 [A fast general thermal simulation model based on MultiBranch Physics-Informed deep operator neural network](https://pubs.aip.org/aip/pof/article-abstract/36/3/037142/3277890/A-fast-general-thermal-simulation-model-based-on?redirectedFrom=fulltext) 被 Physics of Fluids 2024 接受。
 - 添加多目标优化算法 [Relobralo](https://paddlescience-docs.readthedocs.io/zh/latest/zh/api/loss/mtl/#ppsci.loss.mtl.Relobralo) 。

diff --git a/deploy/python_infer/pinn_predictor.py b/deploy/python_infer/pinn_predictor.py
@@ -14,6 +14,7 @@
 
 from typing import Dict
 from typing import List
+from typing import Optional
 from typing import Union
 
 import numpy as np
@@ -106,21 +107,22 @@ def __init__(
     def predict(
         self,
         input_dict: Dict[str, Union[np.ndarray, paddle.Tensor]],
-        batch_size: int = 64,
+        batch_size: Optional[int] = 64,
     ) -> Dict[str, np.ndarray]:
         """
         Predicts the output of the model for the given input.
 
         Args:
             input_dict (Dict[str, Union[np.ndarray, paddle.Tensor]]):
                 A dictionary containing the input data.
-            batch_size (int, optional): The batch size to use for prediction.
-                Defaults to 64.
+            batch_size (Optional[int]): The batch size to use for prediction.
+                If None, input will be directly sent to the model
+                without batch slicing. Defaults to 64.
 
         Returns:
             Dict[str, np.ndarray]: A dictionary containing the predicted output.
         """
-        if batch_size > self.max_batch_size:
+        if batch_size and batch_size > self.max_batch_size:
             logger.warning(
                 f"batch_size({batch_size}) is larger than "
                 f"max_batch_size({self.max_batch_size}), which may occur error."
@@ -143,7 +145,7 @@ def predict(
             ]
 
         num_samples = len(next(iter(input_dict.values())))
-        batch_num = (num_samples + (batch_size - 1)) // batch_size
+        batch_num = (num_samples + (batch_size - 1)) // batch_size if batch_size else 1
         pred_dict = misc.Prettydefaultdict(list)
 
         # inference by batch
@@ -152,9 +154,12 @@ def predict(
                 logger.info(f"Predicting batch {batch_id}/{batch_num}")
 
             # prepare batch input dict
-            st = (batch_id - 1) * batch_size
-            ed = min(num_samples, batch_id * batch_size)
-            batch_input_dict = {key: input_dict[key][st:ed] for key in input_dict}
+            if batch_size:
+                st = (batch_id - 1) * batch_size
+                ed = min(num_samples, batch_id * batch_size)
+                batch_input_dict = {key: input_dict[key][st:ed] for key in input_dict}
+            else:
+                batch_input_dict = {key: input_dict[key] for key in input_dict}
 
             # send batch input data to input handle(s)
             if self.engine != "onnx":

diff --git a/docs/index.md b/docs/index.md
@@ -91,7 +91,9 @@
 
 | 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](./zh/examples/ldc2d_steady.md) | 机理驱动 | MLP | 无监督学习 | - |  |
+| 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 血管瘤](./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)|

diff --git a/docs/zh/api/arch.md b/docs/zh/api/arch.md
@@ -4,36 +4,32 @@
     handler: python
     options:
       members:
-        - Arch
+        - AFNONet
         - AMGNet
-        - MLP
-        - ModifiedMLP
-        - PirateNet
+        - Arch
+        - AutoEncoder
+        - ChipDeepONets
+        - CuboidTransformer
+        - CVit1D
+        - CylinderEmbedding
         - DeepONet
         - DeepPhyLSTM
-        - LorenzEmbedding
-        - RosslerEmbedding
-        - CylinderEmbedding
-        - Generator
+        - DGMR
         - Discriminator
-        - PhysformerGPT2
+        - ExtFormerMoECuboid
+        - Generator
+        - HEDeepONets
+        - LorenzEmbedding
+        - MLP
         - ModelList
-        - AFNONet
-        - PrecipNet
-        - PhyCRNet
-        - UNetEx
-        - USCNN
+        - ModifiedMLP
         - NowcastNet
-        - HEDeepONets
-        - DGMR
-        - ChipDeepONets
-        - AutoEncoder
-        - CuboidTransformer
-        - ExtFormerMoECuboid
         - SFNONet
-        - UNONet
         - TFNO1dNet
         - TFNO2dNet
         - TFNO3dNet
+        - UNetEx
+        - UNONet
+        - USCNN
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/equation.md b/docs/zh/api/equation.md
@@ -12,10 +12,10 @@
         - Laplace
         - LinearElasticity
         - NavierStokes
+        - NLSMB
         - NormalDotVec
         - Poisson
         - Vibration
         - Volterra
-        - NLSMB
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/experimental.md b/docs/zh/api/experimental.md
@@ -14,7 +14,7 @@
         - bessel_i1e
         - fractional_diff
         - gaussian_integrate
-        - trapezoid_integrate
         - montecarlo_integrate
+        - trapezoid_integrate
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/geometry.md b/docs/zh/api/geometry.md
@@ -5,18 +5,18 @@
     options:
       members:
         - Geometry
-        - Interval
-        - Disk
-        - Polygon
-        - Rectangle
-        - Triangle
         - Cuboid
-        - Sphere
+        - Disk
         - Hypercube
         - Hypersphere
+        - Interval
         - Mesh
         - PointCloud
+        - Polygon
+        - Rectangle
+        - Sphere
         - TimeDomain
         - TimeXGeometry
+        - Triangle
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/lr_scheduler.md b/docs/zh/api/lr_scheduler.md
@@ -4,13 +4,13 @@
     handler: python
     options:
       members:
-        - Linear
         - Cosine
-        - Step
-        - Piecewise
-        - MultiStepDecay
-        - ExponentialDecay
         - CosineWarmRestarts
+        - ExponentialDecay
+        - Linear
+        - MultiStepDecay
         - OneCycleLR
+        - Piecewise
+        - Step
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/metric.md b/docs/zh/api/metric.md
@@ -6,12 +6,12 @@
       members:
         - Metric
         - FunctionalMetric
-        - MAE
-        - MSE
-        - RMSE
         - L2Rel
-        - MeanL2Rel
         - LatitudeWeightedACC
         - LatitudeWeightedRMSE
+        - MAE
+        - MeanL2Rel
+        - MSE
+        - RMSE
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/optimizer.md b/docs/zh/api/optimizer.md
@@ -4,12 +4,12 @@
     handler: python
     options:
       members:
-        - SGD
-        - Momentum
         - Adam
         - AdamW
-        - RMSProp
         - LBFGS
+        - Momentum
         - OptimizerList
+        - RMSProp
+        - SGD
       show_root_heading: true
       heading_level: 3
diff --git a/docs/zh/api/visualize.md b/docs/zh/api/visualize.md
@@ -5,17 +5,17 @@
     options:
       members:
         - Visualizer
-        - VisualizerScatter1D
-        - VisualizerScatter3D
-        - VisualizerVtu
         - Visualizer2D
         - Visualizer2DPlot
         - Visualizer3D
-        - VisualizerWeather
         - VisualizerRadar
-        - save_vtu_from_dict
-        - save_vtu_to_mesh
+        - VisualizerScatter1D
+        - VisualizerScatter3D
+        - VisualizerVtu
+        - VisualizerWeather
         - save_plot_from_1d_dict
         - save_plot_from_3d_dict
+        - save_vtu_from_dict
+        - save_vtu_to_mesh
       show_root_heading: true
       heading_level: 3