[Hackathon 6th Code Camp No.15] support neuraloperator by Yang-Changhui · Pull Request #867 · PaddlePaddle/PaddleScience

Yang-Changhui · 2024-04-25T02:52:15Z

PR types

New features

PR changes

Others

Describe

增加neuraloperator模型

paddle-bot · 2024-04-25T02:52:20Z

Thanks for your contribution!

zhiminzhang0830 · 2024-04-26T07:31:52Z

ppsci/arch/fno_block.py

+        except KeyError:
+            padding = [round(p * r) for (p, r) in zip(self.domain_padding, resolution)]
+
+            print(


建议使用ppsci内置的log

zhiminzhang0830 · 2024-04-26T07:32:56Z

ppsci/arch/fno_block.py

+            # of the "padding" list i.e. the last axis of tensor 'x' will be
+            # padded by the amount mention at the first position of the
+            # 'padding' vector. The details about F.pad can be found here:
+            # https://pytorch.org/docs/stable/generated/torch.nn.functional.pad.html


确认注释正确性

zhiminzhang0830 · 2024-04-26T07:40:36Z

ppsci/arch/fno_block.py

+            padded = F.pad(x, padding, mode="constant")
+
+            output_shape = padded.shape[2:]
+


删除多余空格

zhiminzhang0830 · 2024-04-26T07:44:11Z

ppsci/arch/fno_block.py

+        return nn.Identity()
+    else:
+        raise ValueError(
+            f"Got skip-connection type = {type}, expected one of {'soft-gating', 'linear', 'id'}."


id --> identity

zhiminzhang0830 · 2024-04-26T08:15:25Z

ppsci/arch/fno_block.py

+            arg  is only checked when `implementation=reconstructed`. Defaults to False.
+
+    Raises:
+        ValueError: _description_


删除raises

zhiminzhang0830 · 2024-04-26T08:15:57Z

ppsci/arch/fno_block.py

+
+    if implementation == "reconstructed":
+        if separable:
+            print("SEPARABLE")


删除print

zhiminzhang0830 · 2024-04-26T08:16:30Z

ppsci/arch/fno_block.py

+        #     elif weight.name.lower() == 'complexcp':
+        #         return _contract_cp
+        #     else:
+        #         raise ValueError(f'Got unexpected factorized weight type {weight.name}')


删除无意义的注释

zhiminzhang0830 · 2024-04-28T12:23:21Z

ppsci/arch/fno_block.py

+        fixed_rank_modes=False,
+        joint_factorization=False,
+        init_std="auto",
+        fft_norm="backward",


初始化添加类型提示，其他的类也注意一下

zhiminzhang0830 · 2024-04-28T12:27:34Z

ppsci/arch/fno_block.py

+            )
+
+    def forward(
+        self, x: paddle.Tensor, indices=0, output_shape: Optional[Tuple[int]] = None


变量 indices 添加类型提示

zhiminzhang0830 · 2024-04-28T12:29:20Z

ppsci/arch/fno_block.py

+
+    This is provided for reference only,
+    see :class:`neuralop.layers.SpectraConv` for the preferred, general implementation
+    """


更正注释，ppsci没有neuralop.layers.SpectraConv这个路径，另外确认该类是否在代码中有用到

这几个类都没有用到，但是是可选的

…/PaddleScience into add_neuraloperator

zhiminzhang0830 · 2024-04-29T04:05:00Z

ppsci/arch/sfnonet.py

+
+
+def _contract_dense_trick(x, weight_real, weight_imag, separable=False, dhconv=True):
+    # the same as above function, but do the complex multiplication manually to avoid the einsum bug in paddle


“the same as above function” ？这个函数上面没有其他函数呀？

zhiminzhang0830 · 2024-04-29T04:07:59Z

ppsci/arch/sfnonet.py

+
+    if implementation == "reconstructed":
+        if separable:
+            print("SEPARABLE")


确认是否有必要print

zhiminzhang0830 · 2024-04-29T04:08:24Z

ppsci/arch/sfnonet.py

+    elif implementation == "factorized":
+        if isinstance(weight, paddle.Tensor):
+            return _contract_dense_trick
+        # TODO: FactorizedTensor not supported yet


这个注释可以删掉吧

zhiminzhang0830 · 2024-04-29T04:15:25Z

ppsci/arch/sfnonet.py

+
+
+class SphericalConv(nn.Layer):
+    """Spherical Convolution, base class for the SFNO [1]_


注释最后用“.“更合适吧？

zhiminzhang0830 · 2024-04-29T04:16:30Z

ppsci/arch/sfnonet.py

+    """Spherical Convolution, base class for the SFNO [1].
+        .. [1] Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere,
+           Boris Bonev, Thorsten Kurth, Christian Hundt, Jaideep Pathak, Maximilian Baust, Karthik Kashinath, Anima Anandkumar,
+           ICML 2023.


references重复了

zhiminzhang0830 · 2024-04-29T04:17:16Z

ppsci/arch/sfnonet.py

+    Args:
+        in_channels (int): Number of input channels.
+        out_channels (int): Number of output channels.
+        n_modes (int): Number of modes to use for contraction in Fourier domain during


注释中的变量类型与初始化函数中的保持一致

zhiminzhang0830 · 2024-05-06T12:09:09Z

ppsci/arch/fno_block.py

+    """Applies domain padding scaled automatically to the input's resolution
+
+    Args:
+        domain_padding (float): typically, between zero and one, percentage of padding to use.


类型与初始化代码保持一致， Union[float, List[float]]

zhiminzhang0830 · 2024-05-10T09:27:10Z

ppsci/data/dataset/darcyflow_dataset.py

+
+        Returns
+        -------
+        torch.tensor


函数注释修改下，建议注释风格修改为PaddleScience风格

zhiminzhang0830 · 2024-05-10T09:27:44Z

ppsci/data/dataset/darcyflow_dataset.py

+
+        # x is in shape of batch*n or T*batch*n
+        # x = (x.view(self.sample_shape) * std) + mean
+        # x = x.view(-1, *self.sample_shape)


不需要的注释删除吧

zhiminzhang0830 · 2024-05-10T09:30:49Z

ppsci/data/dataset/darcyflow_dataset.py

+        return x
+
+
+def count_params(model):


确认此函数是否有使用

zhiminzhang0830 · 2024-05-10T09:40:55Z

ppsci/data/dataset/darcyflow_dataset.py

+    50 samples at resolution 32x32.
+
+    Args:
+        test_resolutions (List[int,...]): The resolutions to test dataset. Default is [16, 32].


完善docstring，与初始化函数的入参保持一致，缺少train_resolution，记得补充完整。test_resolutions参数的docstring的默认值也需要与初始化入参保持一致

zhiminzhang0830 · 2024-05-10T09:56:25Z

ppsci/data/dataset/spherical_swe_dataset.py

+    50 samples at resolution 64x128.
+
+    Args:
+        test_resolutions (List[str,...]): The resolutions to test dataset. Default is ["34x64","64x128"].


完善docstring

… into add_neuraloperator

…/PaddleScience into add_neuraloperator

zhiminzhang0830 · 2024-05-11T09:44:41Z

docs/zh/api/data/dataset.md

添加 SphericalSWEDataset

因为这个数据集是我使用pytorch原代码生成的数据，直接保存的npy文件，这样还需要写进去吗

zhiminzhang0830 · 2024-05-11T09:45:57Z

examples/neuraloperator/conf/sfno_swe_pretrain.yaml

+  pretrained_model_path: ./outputs_sfno_pretrain/checkpoints/best_model.pdparams
+  export_path: ./inference/uno/uno_darcyflow
+  pdmodel_path: ${INFER.export_path}.pdmodel
+  pdpiparams_path: ${INFER.export_path}.pdiparams


pdpiparams_path --> pdiparams_path 全部替换一下

zhiminzhang0830 · 2024-05-11T09:52:37Z

ppsci/data/dataset/darcyflow_dataset.py

+        encoding (str): The type of encoding. Default is 'channel-wise'.
+        channel_dim (int): The location of unsqueeze. Default is 1.
+            where to put the channel dimension, defaults size is batch, channel, height, width
+        training (str): Wether to use training or test dataset. Default is 'train'.


其他数据集中使用 training 参数表示该数据集是否用于训练，使用bool类型。在此数据集中，training 参数还用于表示测试时的数据选择，与变量名称”training“不太相符，建议修改为其他更有意义的变量名称

zhiminzhang0830 · 2024-05-11T09:53:16Z

ppsci/data/dataset/spherical_swe_dataset.py

+            Defaults to None.
+        test_resolutions (Tuple[str, ...], optional): The resolutions to test dataset. Defaults to ["34x64", "64x128"].
+        train_resolution (str, optional): The resolutions to train dataset. Defaults to "34x64".
+        training (str, optional): Wether to use training or test dataset. Defaults to "train".


zhiminzhang0830 · 2024-05-11T09:54:15Z

examples/neuraloperator/earthformer.md

与本PR无关，记得删除

zhiminzhang0830 · 2024-05-11T09:58:19Z

examples/neuraloperator/train_sfno.py

+    input_data = data["x"][0].reshape(1, *data["x"].shape[1:]).astype("float32")
+    label = data["y"][0][0, ...].astype("float32")
+
+    model = ppsci.arch.SFNONet(


好像还是使用动态图的形式进行预测的？并没有使用export的静态图模型进行预测？

是动态图形式进行预测的，因为导出静态图模型进行预测时，结果和动态图不一样，可能是因为使用虚数的缘故，也可能是独有的API导致的导出模型的网络权重有问题，跟动态图的网络权重不一样，这个之前给你说过

…/PaddleScience into add_neuraloperator

Yang-Changhui · 2024-05-20T08:11:28Z

paddle使用dev版本

zhiminzhang0830 · 2024-05-26T05:20:09Z

examples/neuraloperator/train_uno.py

+        sup_validator_32.name: sup_validator_32,
+    }
+
+    model = ppsci.arch.TFNO2dNet(


这个地方应该是UNO的模型吧

zhiminzhang0830 · 2024-05-26T05:20:45Z

examples/neuraloperator/conf/tfno_darcyflow_pretrain.yaml

+    scheduler_T_max: 500
+  wd: 1.0e-4
+  batch_size: 16
+  pretrained_model_path: ./pretrainmodel/tfno_pretrain.pdparams


直接设置成null吧，另外两个也改下

zhiminzhang0830 · 2024-05-26T05:23:15Z

ppsci/arch/fno_block.py

+        n_layers: int = 1,
+        max_n_modes: int = None,
+        use_mlp: bool = False,
+        mlp: Optional[dict[float, float]] = None,


此处dict应该为Dict, 并在文件开头添加：from typing import Dict，其他文件也有类似问题，建议统一检查

zhiminzhang0830 · 2024-05-26T05:23:54Z

examples/neuraloperator/train_uno.py

+    ax.set_title("Model prediction")
+    plt.xticks([], [])
+    plt.yticks([], [])
+    plt.savefig(cfg.output_dir + "123.png")


此处123.png，作为文件名称有什么含义么

…/PaddleScience into add_neuraloperator

zhiminzhang0830 · 2024-05-26T10:09:44Z

examples/neuraloperator/train_tfno.py

+    solver.export(input_spec, cfg.INFER.export_path)
+
+
+# 使用静态图推理出错


现在推理还有问题么

zhiminzhang0830 · 2024-05-26T10:10:09Z

examples/neuraloperator/predictor.py

+        """
+        if batch_size != 1:
+            raise ValueError(
+                f"FNOPredictor only support batch_size=1, but got {batch_size}"


FNOPredictor --> SFNOPredictor

…/PaddleScience into add_neuraloperator

zhiminzhang0830

LGTM， TODO：add doc

) * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator

) * add Solver.finetune() (#755) * 【PPSCI Doc No.20】ppsci.arch.DeepPhyLSTM (#756) * [Add] phylstm examples * [Change] phylstm examples * [Change] remove blank line * clear differentiation cache in visu_forward to avoid OOM problem (#757) * update docstring (#758) * 【PPSCI Doc No.104-105】 (#759) * update docstring * remove spaces in args * update * remove extra blank line * 【Hackathon 5th No.63】 PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs (#674) * Add files via upload * Create readme.md * Add files via upload * Update __init__.py * Add files via upload * Add files via upload * add * add * add * add * add * add * add * add * add * add * a * a * Update phycrnet.md * Update phycrnet.md * Update phycrnet.md * a * d * d * a * a * a * a * a * a * p * a * a * a * update .md file * update .md file * update .md file * fix * edit md * eval * m * m * edit * edit --------- Co-authored-by: WG <39621324+wangguan1995@users.noreply.github.com> Co-authored-by: wangguan <772359200@qq.com> * [Doc] Add more contrib and more installtion method (#760) * add 3 install method in README.md * add more contributors * [Doc] Add tutorial and fix docs (#766) * (WIP)Add tutorial page * fix document * fix * change split_to_dict and concat_to_tensor to staticmethod * update batch_index class variable for all datasets * move legend to outter-right of curve box and set dpi to 200 * add 1 more aistudio url * [Fix] Update copyright and docstrings (#761) * update copyright header * update docstring of PhyCRNet * doc106 (#762) * set encoding to utf-8 when reading content from README.md during pip install (#768) * doc108-109 (#764) * remove python3.7 in docker (#765) * remove python3.7 * update * 【PPSCI Doc No.107】update doc for `ppsci.visualize.save_vtu_to_mesh` (#763) * doc107 * fix * [Example] Add RegAE example (#660) * add RegAE example * add RegAE --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * [Enh] add validation for hydra config (#769) * add validation for hydra config * update unitest for pydantic * fix for OptimizerList * fix * 【Hackathon 5th No.54】NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations (#670) * Add files via upload * add * add * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * a * edit * m * edit * a * Update nsfnet4.md * m * m * Update nsfnet4.md * finish * m * debug * edit * add * a * a * a * a * a * a * a * d * Update nsfnet4.md * d * d * d * d * over * reformat docs * fix inference * fix lr scheduler --------- Co-authored-by: WG <39621324+wangguan1995@users.noreply.github.com> Co-authored-by: wangguan <772359200@qq.com> * specify pydantic >= 2.5.x or field_validator can not be imported from pydantic 1.x version (#770) * add YingLong model (#771) * add yinglong inference code * add readme file for yinglong * update yinglong predict code * add copyright in predict_12layers.py * update readme * add reference for timefeatures.py * update predict_12layers and readme * [Doc] Add description of yaml (#774) * (WIP)fix doctest and refine document * update docs * fix wrong code in ldc2d * update code * update paranoma * fix * refine doc * Yinglong infer (#772) * add yinglong inference code * add readme file for yinglong * update yinglong predict code * add copyright in predict_12layers.py * update readme * add reference for timefeatures.py * update predict_12layers and readme * add visualize and update readme * add figure for yinglong * update yinglong readme * fix readme for yinglong * add predict for yinglong 24 layers * update readme * add plot for yinglong * update predict code * update readme * update file path * add version check * fix doc string * update readme * update readme (#775) * set create_graph=False before eval (#776) * [Fea] Support python inference (#773) * [Doc] Add pretrained model for laplace2d & refine comments (#639) * update laplace2d pretrained model * remove 'after finished training' comment in evaluate function * update README.md * add deploy module for aneurysm * update code * update aneurysm code * update code * update code * update code * update aneurysm document * update export and inference document * fix docstring * [Fix] restore 'by_epoch' for SchedulerList and fix EPNN (#777) * restore 'by_epoch' for SchedulerList * fix for epnn * [Fix]fix data transform error (#779) * [Fix]fix data transform error * [Update]add 'auto_collation' for some examples * API 文档补全LorenzEmbedding,RosslerEmbedding * Update embedding_koopman.py * Update embedding_koopman.py * Revert "[Fix]fix data transform error (#779)" (#781) This reverts commit 6823a3e. * [Update]update setting of 'auto_collation' and fix errors (#783) * set 'auto_collation' false when using data transform * fix data transform error of topopt example * update document (#782) * update Graphcast to document (#784) * fix url of GraphCast in index.md (#785) * [Refine] Refine yinglong code (#786) * refine yinglong predictor and use config instead of argparser * modify README of yinglong * fix for review * add requirements for yinglong (#787) * [Docker] Update dockerfile & refine aneurysm (#789) * update pymesh package and dockerfile for python3.9 * refine aneurysm code for export and inference * install requirements.txt before executing setup.py for pymesh * revert random permutation from numpy to paddle (#792) * 【PPSCI Doc No.9】 ppsci.data.dataset.VtuDataset (#791) * Add docx * Apply suggestions from code review * Apply suggestions from code review * [Fea] Support onnx and TensorRT inference (#794) * support onnx inference in base Predictor and PINNPredictor * support exporting onnx model after exporting paddle inference models via argument 'with_onnx' * support TensorRT for aneurysm and add TensorRT example in document * 【PPSCI Export&Infer No. 29】 add export and inference (#793) * add export and inference * update * 【PPSCI Export&Infer No.3】euler_beam (#796) * 【PPSCI Export&Infer No.3】euler_beam * Update examples/euler_beam/euler_beam.py Co-authored-by: HydrogenSulfate <490868991@qq.com> * update config --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * Move 2 tensor initialization to lazy call to prevent using GPU memory when start program in non-gpu mode(such as cpu) (#795) * 【PPSCI Export&Infer No.4】laplace2d (#797) * [Doc] Fix pipe document & refine inference guide (#798) * correct pretrainde_model_path of Pipe Flow(test=document_fix) * refine inference document * fix significant figures to 2 for tidy plot * increase indention * [Fea] Add ModifiedMLP (#799) * Add ModifiedMLP * limit hidden_size to type int for ModifiedMLP * fix f-string * 【PPSCI Export&Infer No.5】lorenz (#801) * 【PPSCI Export&Infer No.5】lorenz * fix bug * 【PPSCI Export&Infer No.6】rossler (#803) * API 文档补全Generator (#804) * fix lorenz/rossler export and infer (#805) * add embedding model to PhysformerGPT2 for infer * modify export and inference code of lorenz * fix export command * fix export and infer of rossler * fix doc * fix error message in generate method * fix docstring * refine code (#806) * 【PPSCI Export&Infer No.7】 volterra_ide (#807) * 【PPSCI Export&Infer No.7】 volterra_ide * fix docstyle * Allow initialize dataloader without specifying 'sampler' (#809) * [Add]MRMSDataset (#810) * [Add]MRMSDataset * fix code and style * [Fea] Support tensorboardX and add corresponding guidance (#812) * support tensorboardX for viv as demo and add tensorboardX guide in user_guide.md * fix comma * Fix sot sci error (#815) * add nsys file * add nsys file * add nsys file * fix paddle sot error * fix code style * chip heat simulation (#808) * add bubble datafile test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code * add bubble data * add bubble code * delete mat file * delete mat file * bubble code * delete mat file * add some modify * add some modifications * add some modifications * add some modifications * add some modifications * add some modification * add some modification * add some modification * add some modification * add some modification * add some modification(test=document_fix) * add some modification * add some modification * add some modification * add some modification * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code for chip heat simulation * add some code for chip heat simulation * add some code for DGMR * add some code for chip * add some code for chip * deleted dgmr code * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * Update examples/chip_heat/conf/chip_heat.yaml --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * modified: docs/zh/examples/chip_heat.md (#820) * add bubble datafile test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code * add bubble data * add bubble code * delete mat file * delete mat file * bubble code * delete mat file * add some modify * add some modifications * add some modifications * add some modifications * add some modifications * add some modification * add some modification * add some modification * add some modification * add some modification * add some modification(test=document_fix) * add some modification * add some modification * add some modification * add some modification * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code for chip heat simulation * add some code for chip heat simulation * add some code for DGMR * add some code for chip * add some code for chip * deleted dgmr code * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * modified some code for chip heat * 【PPSCI Doc No.58、59、60】Mesh.from_pymesh、translate、scale (#818) * update mesh.py * update mesh.py * [Doc] Fix url in chip_heat document (#822) * add bubble datafile test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code * add bubble data * add bubble code * delete mat file * delete mat file * bubble code * delete mat file * add some modify * add some modifications * add some modifications * add some modifications * add some modifications * add some modification * add some modification * add some modification * add some modification * add some modification * add some modification(test=document_fix) * add some modification * add some modification * add some modification * add some modification * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code for chip heat simulation * add some code for chip heat simulation * add some code for DGMR * add some code for chip * add some code for chip * deleted dgmr code * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * modified some code for chip heat * modified some code for chip heat * [Fix] Fix doctest (#821) * fix(test=document_fix) * pretty evaluation output with prettytable * fix code failed in doctest * Revert "Merge branch 'pretty_eval_output' into develop" This reverts commit 66cded1, reversing changes made to 18ea97a. * skip mesh example code in geometry/mesh.py for requiring pymesh installtion * skip more code for doctest * [Fix]dtype of RadarDataset's data (#823) * 【PPSCI Doc No.38-40】 (#826) * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix --------- Co-authored-by: krp <2934631798@qq.com> * remove seed and directory code to slim laplace2d exmaples (#824) * [Fea] Support nvtx profiling (#825) * support nvtx profiling via NVTX=1 * rename trainer to solver * add user guide for NVTX * refine code of paddle.framework.core and add cache for 3 context_manager of Solver * update nsys chapter in user_guide * fix solver.py * Dgmr (#813) * add bubble datafile test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code * add bubble data * add bubble code * add some code for chip * add some code for DGMR * add some code for DGMR * add some code for DGMR * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * add some dgmr code * check if is directory befoe mkdirs (#827) * [Fix] Replace os.path.isdir with len (#830) * replace os.path.isdir with len * enumerate from 0 * add quasi-random sampling method: Halton (#828) * Update solver.py (#831) 修改osp.isdir为len * 【PPSCI Doc No.66-74】 (#829) * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * fix api docs in the timedomain * fix api docs of timedomain * fix api docs of timedomain --------- Co-authored-by: krp <2934631798@qq.com> Co-authored-by: HydrogenSulfate <490868991@qq.com> * [Enh] Refactor sum aggregator (#834) * add Sum loss aggregator * simplify loss aggregation code in train.py and add check for AGDA and PCGrad when used with amp * add check for using L-BFGS with use_amp=True * Refine Relobralo * Fix docstring of timedomain.py * remove unnecessary code in train.py * automatically download *.pdeqn file if available when download pretrained model * wrap func generated by symbolic module with DDP * fix Relobralo * initialize loss with 0.0 instead of first loss * 【PPSCI Doc No.41-57】 (#833) * fix docs bugs * fix docs bugs * fix codestyle bug * fix codestyle bugs * fix codestyle bugs * fix some bugs * fix codetype error * fix other bugs * fix typehint bugs * fix other bugs * fix codestyle bug * fix codestyle bug * add skip_prune_program arg for Solver.export (#835) * 【PPSCI Export&Infer No.23】viv (#832) * eadd export and inference for viv * add doc * fix viv export&infer * Rewriting function * fix viv export&infer * [Doc] Add more contributors and refine several docstrings (#836) * auto generate contributors instead of adding manually * refine return type of docstrings * 【PPSCI Doc No.61-65】 (#839) * fix doc bugs * fix codestyle bugs * [Doc] Fix description for mkldnn (#837) * fix description for mkldnn * merge 3 visualization chapter into one chapter * initialize loss with first constraint loss instead of 0.0, and change random seed of euler_beam for better l2error * update euler_beam doc * fix return type of PDE.set_state_dict * Update XPINN_2D_PoissonsEqn.py (#842) * support enabling prim via ++prim=1 (#843) * 【PPSCI Doc No.23、25-29、31-34、97】 (#840) * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * fix api docs in the timedomain * fix api docs of timedomain * fix api docs of timedomain * ppsci api docs fixed * ppsci api docs fixed * ppsci api docs fixed --------- Co-authored-by: krp <2934631798@qq.com> Co-authored-by: HydrogenSulfate <490868991@qq.com> * 【PPSCI Doc No.35-37】 (#846) * docs: add examples for api No.35-37 * Update ppsci/equation/pde/base.py * Update ppsci/equation/pde/base.py * Update ppsci/equation/pde/base.py --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * Bubble net (#847) * add bubble datafile test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code test=develop * add bubble code * add bubble data * add bubble code * delete mat file * delete mat file * bubble code * delete mat file * add some modify * add some modifications * add some modifications * add some modifications * add some modifications * add some modification * add some modification * add some modification * add some modification * add some modification * add some modification(test=document_fix) * add some modification * add some modification * add some modification * add some modification * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code test=develop * add some code for chip heat simulation * add some code for chip heat simulation * add some code for DGMR * add some code for chip * add some code for chip * deleted dgmr code * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * add some code for chip heat * modified some code for chip heat * modified some code for chip heat * modified some code for chip heat * [Example] Add allen cahn example (#845) * allow empty optimizer when saving checkpoint * add model averaging module * fix return dtype inconsistency with global dtype * use python func instead of sympy function for pow(u,3) get a bit poor L2 error than multiply(u*u*u) * refine AllenCahn docstring * support save and load for average model module * add 3 ema unitests * update 2023 to 2024 * add ema config pydantic scheme * add avg_range for SWA * update field_validator for swa and ema * support period embedding for MLP * Keep non-float data when reading file * update ema and save_load, printer and eval, solver module code * add allen_cahn example * refine code * save buffer and non-grad required params in ema * add unitest for ema with buffer * fix epoch_ema saving * add unitest for ema state_dict * refine allen_cahn_plain.py * fix string to floating conversion in reader.py * fix string to floating conversion in reader.py * remove print code in solver * Update allen_cahn_plain.py * Update misc.py --------- Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> * 【benchmark】fix benchmark model name (#850) * add max_mem_reserved for benchmark * add max_mem_reserved for benchamrk * fix benchmark model name * [Example] Add allen_cahn causal train with fourier feature and random weight factorization (#848) * allow empty optimizer when saving checkpoint * add model averaging module * fix return dtype inconsistency with global dtype * use python func instead of sympy function for pow(u,3) get a bit poor L2 error than multiply(u*u*u) * refine AllenCahn docstring * support save and load for average model module * add 3 ema unitests * update 2023 to 2024 * add ema config pydantic scheme * add avg_range for SWA * update field_validator for swa and ema * support period embedding for MLP * Keep non-float data when reading file * update ema and save_load, printer and eval, solver module code * add allen_cahn example * refine code * save buffer and non-grad required params in ema * add unitest for ema with buffer * fix epoch_ema saving * add unitest for ema state_dict * refine allen_cahn_plain.py * fix string to floating conversion in reader.py * fix string to floating conversion in reader.py * update code and refine document * correct initialization for RWF * update docstring for arg 'random_weight' of mlp * update docstrings * add causal fourier rwf config * fix code in mlp.py * refine code in mse.py * add ema document file(test=document_fix) (#853) * [New example] Add nls-mb example (#838) * add NLS-MB example * fix * fix * fix * fix * modify * modify * modify * fix * replace deprecated 'FieldValidationInfo' with 'ValidationInfo' (#855) * check return type of FunctionalLoss (#854) * [Docker] Add docker image (#856) * execute 'ldconfig' after /bin/bash automatically * add_dockerhub * refine doc * update base image to paddle official image(test=document_fix) * update code * update code * 【PPSCI Export&Infer No.24】 biharmonic2d (#858) * [SCI Export&Infer No.24] biharmonic2d * P[PSCI Export&Infer No.724] biharmonic2d fix * [Fix] Fix NLS-MB document and code (#859) * execute 'ldconfig' after /bin/bash automatically * add_dockerhub * refine doc * update base image to paddle official image(test=document_fix) * Fix NLS-MB examples code and document * Update YingLong1 README.md (#861) * Update YingLong1 README.md * Update README.md * add '_' to initializer.glorot_normal * add allen_cahn_default.yaml * [Doc] Add anno for eval (#863) * add annotation for eval.py * add NLS example into index and README * rename yinglong to yinglong1 (#862) * add allen-cahn document * update pymesh install package * 【PPSCI Export&Infer No.22】VP_NSFNet4 (#864) * [SCI Export&Infer No.24] biharmonic2d * P[PSCI Export&Infer No.724] biharmonic2d fix * add export&infer nsfnet4 * add export&infer nsfnet4 * update pymesh install package (#865) * [Refine] Refine evaluation output (#866) * fix(test=document_fix) * pretty evaluation output with prettytable * remove epoch id when ony evaluating * hidden epoch information when not evaluating on flying * [Enh] Add numpy solver in config solvers (#869) * support registering numpy config solvers when parsing attribute of numpy from config * remove permutation code * avoid duplicated register * [API] Add chamfer loss (#871) * add chamfer loss * update development.md * update example of chamfer loss docstring * fix doctest for ChamferLoss * support batch comupute for chamferloss * add-earthformer (#870) * del arch.md in data (#872) * [Add]Add competition&IJCAI_2024 submodule (#873) * [Add]Add competition&IJCAI_2024 code * update README * add IJCAI 2024 CAR competition to inedx.md and fix docstrings in cuboid_transformer.py(test=document_fix) (#874) * [Update]update competition description (#876) * Fix typo (#881) * fix typo for correcting 'direcotry' to 'directory' * fix typo for correcting 'unchaned' to 'unchanged' * [Fix] Fix inference path typo (#880) * fix(test=document_fix) * fix typo for correcting 'pdpiparmas' to 'pdiparams' * add left bracket for docstring of CuboidSelfAttentionLayer * 【PPSCI Export&Infer No.15-16】 (#875) * fix doc bugs * fix codestyle bugs * 【PPSCI Export&Infer No.15-16】 * fix codestyle bug for PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs * updata_ijcai_car_submodule (#882) * 【PPSCI Export&Infer No.25】bracket (#878) * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * fix api docs in the timedomain * fix api docs of timedomain * fix api docs of timedomain * ppsci api docs fixed * ppsci api docs fixed * ppsci api docs fixed * add export and infer for bracket * updata bracket doc * solve conflict according to the branch named develop * Update examples/bracket/conf/bracket.yaml * Update examples/bracket/conf/bracket.yaml * Update examples/bracket/conf/bracket.yaml * add export&inference for bracket --------- Co-authored-by: krp <2934631798@qq.com> Co-authored-by: HydrogenSulfate <490868991@qq.com> * add document of python_infer with depoly module (#885) * 【PPSCI Export&Infer No.11-12】 (#883) * fix doc bugs * fix codestyle bugs * 【PPSCI Export&Infer No.15-16】 * fix codestyle bug for PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs for 【PPSCI Export&Infer No.15-16】 * fix bugs for 【PPSCI Export&Infer No.15-16】 * fix codestyle bugs * 【PPSCI Export&Infer No.11-12】 * change predictor * fix bugs in change predictor * cancel extra doc commit * fix codestyle bugs * Update examples/cylinder/2d_unsteady/cylinder2d_unsteady_Re100.py * Update examples/cylinder/2d_unsteady/transformer_physx/train_transformer.py * Update examples/cylinder/2d_unsteady/cylinder2d_unsteady_Re100.py * Update examples/cylinder/2d_unsteady/transformer_physx/train_transformer.py * Update examples/cylinder/2d_unsteady/transformer_physx/train_transformer.py * cancel extra changes * cancel extra changes * update examples/cylinder/2d_unsteady/transformer_physx/conf/transformer.yaml --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * 【PPSCI Export&Infer No.21】tempoGAN (#884) * add tempoGAN export&infer * fix tempoGAN.md * fix tempoGAN.md * fix tempoGAN.py * [Doc&Refine] Add IJCAI competetion in README (#886) * add ijcai 2024 competetion information in README * refine symbolic module * Fix document(test=document_fix) * fix for pdiparams_path * [Hackathon 6th Code Camp No.15] support earthformer docs (#877) * add-earthformer * add-earthformer-doc * add-earthformer-doc * add-erthformer-doc * add-earthformer * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc --------- Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> * Update mkdocs.yml (#888) * 【PPSCI Export&Infer No.20】shock_wave (#890) * add shock_wave export&infer * Update examples/shock_wave/shock_wave.py * Update examples/shock_wave/shock_wave.py --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * 【PPSCI Export&Infer No.9】Bubble (#887) * 【PPSCI Export&Infer No.9】 * update examples/bubble/conf/bubble.yaml * fix codestyle bugs * Update examples/bubble/bubble.py * update examples/bubble/bubble.py --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * modify earthformer-doc (#891) * add-earthformer * add-earthformer-doc * add-earthformer-doc * add-erthformer-doc * add-earthformer * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc * add-earthformer-doc --------- Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> * 【PPSCI Export&Infer No.30】heat_exchanger (#892) * 【PPSCI Export&Infer No.30】heat_exchanger * fix codestyle bug * update examples/heat_exchanger/heat_exchanger.py * fix codestyle bugs * Update heat_exchanger.py Fix and simplify code --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * add export&infer 26-27 (#893) * [Fea] Support detach_keys argument for all PDE (#889) * fully support detach_keys argument for all PDE * add unitest for detach option * fix access for 'name' when exp do not have 'name' attribute * fix unitest * add example code for _apply_detach * fix test_pde_base * [Fix] Fix phycrnet bug (#894) * fix phycrnet bug * Update examples/phycrnet/functions.py Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> * Update examples/phycrnet/functions.py Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> --------- Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> * [Doc] Update links of cooperation projects (#898) * fix(test=document_fix) * optimize importing * 添加共创计划项目链接 * [Ehn] Enhance config module (#899) * support default config content in config module and remove deprecated AttrDict series code * update corresponding unitests * update develop code * 【PPSCI Export&Infer No.13】 darcy2d (#900) * 【PPSCI Export&Infer No.13】 darcy2d * Update examples/darcy/darcy2d.py --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * Add export & inference for hPINNs (#902) * feat: add export and infer functions for hpinns * fix:register transform brfore export * 【PPSCI Export&Infer No.2】Add export & inference for DeepONet (#901) * add DeepONet export and infer * update docstring of geometry * Update deeponet.py * Update deeponet.py * [Upadte]update plotting of hpinn's inference (#903) * [Upadte]update plotting of hpinn's inference * update1 * [Fix] Fix fractional poisson 2d (#904) * Fix fractional_poisson_2d * update fractional_poisson_2d * [Doc&Fix] Update config doc and correct API (#905) * update config document and adapt viv code to new config module * update 'how to use optuna' in document * Fix * 【PPSCI Export&Infer No.35】nowcastnet (#895) * nowcastnet.py * nowcastnet.py * nowcastnet.py * Update examples/nowcastnet/nowcastnet.py Co-authored-by: HydrogenSulfate <490868991@qq.com> * Update examples/nowcastnet/nowcastnet.py Co-authored-by: HydrogenSulfate <490868991@qq.com> * nowcastnet * nowcastnet --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * Fix cylinder2d_unsteady_transformer_physx (#906) * [Fea] Add PirateNet and update allen_cahn document (#907) * Add PiraNet and update allen_cahn document * fix example code for mlp.py * rename pira to pirate * update AIStudio link for allen cahn * [Fix] Fix output_dir for visualDL and tensorboardX (#908) * fix output_dir for visualDL and tensorboardX * update scikit-learn<1.5.0 for incompatible upgrad * update docs(test=document_fix) (#909) * [Hackathon 6th Code Camp No.15] support neuraloperator (#867) * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * [Fix] Fix document requirement and update yaml (#910) * add dependencies to dynamic in pyproject.toml * Add --create-dirs in curl scripts for creating directory automatically * remove visualdl from requirements.txt * use true/false instead of True/False for compatibility * update some links * fix visualdl * [Fix] Correct desciprtion of epsilon of AllenCahn equation (#911) * Correct desciprtion of epsilon of AllenCahn equation * fix seed for test_detach * Add allen cahn sota (#879) * add allen cahn ntk * update code * add allen cahn ntk * update code * update code * update code * 修改配置 --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * 【Hackathon 6th No.39】XPINN 迁移至 PaddleScience (#849) * add XPINNs example * comment * add conf file * refine code * fix comment * fix data type * fix data type * Update examples/xpinn/plotting.py * Update examples/xpinn/conf/xpinn.yaml * refine code * refine doc * refine doc * fix doc * fix bugs --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * [Doc] Add evaluation for xpinn and add to homepage (#912) * add evaluation for xpinn and refine doc * update Examples in AllenCahn docstring * fix export and infer (#916) * update example code for PINNPredictor (#918) * auto build and upload develop pip whl to pypi when commiting (#920) * fix for 3.10 (#921) * [Refine] Refine loss and metric module (#919) * return loss dict instead of loss summation for all loss.forward * adapt all mtl module for Dict[str, Tensor] type of input losses * fix * remove 'area' in Constriant.output_keys * fix eval.py * fix code * fix examples in func.py * fix examples in func.py * Fix for MSELossWithL2Decay and train_enn.py * fix doctest in loss/mse.py * fix epnn * fix * [Doc] Refine user guide (#922) * fix code and refine userguide * print log when reach the training max_steps * update docs * [Example] Add ldc 2d Re1000 and Re3200 example (#924) * update piranet for ldc re3200 case(WIP) * add ldc_2d_Re1000 plain example * add ldc_2d_Re3200_piratenet and ldc_2d_Re3200_sota * refine code * refine docstrings * add missing blank line for docstrings * refine docstrings * replace lowercase to uppercase for first word in sentence * add ldc_2d_re3200_piratenet and ldc_2d_re3200_sota * remove redundant files * fix linenum * fix doctest * fix for allen_cahn * [Doc] Update ldc2d doc and README (#925) * update ldc2d doc * update RAEDME * 【PPSCI Export&Infer No.31】heat_pinn (#926) * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * ppsci.equation.PDE.parameters/state_dict/set_state_dict api fix * fix api docs in the timedomain * fix api docs of timedomain * fix api docs of timedomain * ppsci api docs fixed * ppsci api docs fixed * ppsci api docs fixed * add export and infer for bracket * updata bracket doc * solve conflict according to the branch named develop * Update examples/bracket/conf/bracket.yaml * Update examples/bracket/conf/bracket.yaml * Update examples/bracket/conf/bracket.yaml * add export&inference for bracket * add export and infer for heat_pinn * add export and infer for heat_pinn * Update examples/heat_pinn/heat_pinn.py * Update examples/heat_pinn/heat_pinn.py * Update examples/heat_pinn/conf/heat_pinn.yaml --------- Co-authored-by: krp <2934631798@qq.com> Co-authored-by: HydrogenSulfate <490868991@qq.com> * [Doc] Refine doc (#927) * remove vtk for slim requirements.txt * fix document of ldc2d_steady.md * refine grad_norm * remove redundant profiler.py file * refine docs * fix gradnorm * restore gradnorm to original version * remove pyvista from requirements.txt * add nightly build pip .whl url (#928) * Support gh pages (#929) * update develop mkdocs * add mike plugin to support deploying document in github pages * remove pycamotk for submodules (#930) * add workflows for github pages * update mkdocs.yml * update ai4s_universal_platform branch for gh-page * only set default to latest when current branch is develop * fix ci.yml * fix alias * use develop instead of latest * remove ci.yml in develop branch * [Fix] Fix eval (#931) * update develop mkdocs * allow alias for mike * fix and refine eval.py * fix * [Hackathon 6th Code Camp No.15] support neuraloperator docs (#917) * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator * add-neuraloperator-doc * add-neuraloperator-doc * move-paddle-harmonics * add-neuraloperator-doc * add-neuraloperator-doc * add-neuraloperator-doc * add-neuraloperator-doc * add-neuraloperator-doc * add-neuraloperator-doc * add-neuraloperator-docs * add-neuraloperator-docs * add-neuraloperator-docs * add-neuraloperator-doc * add-neuraloperator-doc * add montecarlo integrate api (#932) * add montecarlo integrate api * Update ppsci/experimental/math_module.py * Update ppsci/experimental/math_module.py * Update ppsci/experimental/math_module.py * Update ppsci/experimental/math_module.py * Update ppsci/experimental/math_module.py * fix code format error --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * 【Hackathon 6th No.37】GraphCastNet 代码迁移至 PaddleScience (#897) * add GraphGridMeshDataSet * add graphcast model and example * refine code and visualization * add license * fix bugs * fix ci errors * fix ci errors * fix ci errors * fix ci errors * fix ci errors * add docs * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * refine docs * fix comments * fix comments * fix comments * fix * delete atmospheric_utils.py * fix ci errors * fix * fix comments * fix * add transform in graphcast * fix model bugs * fix * fix docs * [Doc&Fix] Fix compatibility with isort and black and refine install_setup and graphcast doc (#934) * update develop mkdocs * allow alias for mike * add pymesh test notation for py310 and fix isort conflict with black * use warning instead of assert for duplicated metric name * fix amgnet for precision promotion is deprecated between int32/64 * [Doc] Refine doc and code (#935) * update develop mkdocs * allow alias for mike * fix code * use full instead of to_tensor * reset time statistics after printing * modify yinglong (#937) * modify yinglong * refine * update adr example(pre) (#938) * add Extformer-MoE example by HKUST(GZ) (#933) * add extformer-moe * fix 0624 * fix 0624 * Delete outputs_extformer_moe_pretrain directory * Delete docs/zh/examples/extformer_moe_figs directory * Update extformer_moe.md * Update extformer_moe_utils.py * Update extformer_moe.md * Update ppsci/data/dataset/__init__.py Co-authored-by: HydrogenSulfate <490868991@qq.com> * Update ppsci/data/dataset/ext_moe_enso_dataset.py Co-authored-by: HydrogenSulfate <490868991@qq.com> * fix merge review issues * fix merge 240629 * fix 240701 * fix 240701_ * fix 240701__ * fix 240701___ * Update ext_moe_enso_dataset.py * Update docs/zh/examples/extformer_moe.md Co-authored-by: HydrogenSulfate <490868991@qq.com> * Update docs/zh/examples/extformer_moe.md Co-authored-by: HydrogenSulfate <490868991@qq.com> * Update ppsci/data/dataset/ext_moe_enso_dataset.py --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> * [Fix] Fix extformer-moe (#940) * fix&refine extformer code and docs * replace paddle.nn. with nn. * update Extformer-MoE in docs * [Example] Add adv_cvit and ns_cvit (#939) * update develop mkdocs * allow alias for mike * update CViT code(WIP) * update CViT code(WIP) * update validate code * update code * update code * refine code * refine docs * update docs * update export&inference code * update ns cvit code(WIP, not aligned) * update reprod code * rename block name according to their class * add more config yamls * fix data/__init__ * fix * refine code and add more annotations * update code * update TRT steps * change pos/time embedding from buffer to trainable parameters * use interpolation for spatial_dims * remove interpolation * update config * fix std of normal initializer * update outputfile * add einops into req * restore l2_rel * refine eval checking and logging * update example code of FunctionalBatchTransform * update pretrained url and plot code * add cvit doc * update adv_cvit doc * rename title for adv_cvit.md * update docs * update docs * fix zh/examples/extformer_moe.md * update docs * refine code * [Fix] Fix batch indexing failed in phylstm2 (#941) * fix batch indexing failed in list: * fix chapter number of adv_cvit.md(test=document_fix) * [Doc] Add requirements.txt for AMGNet (#942) * remove print code * add req for amgnet * [Fix] Fix phylstm (#943) * fix phylstm running error * update version warning * fix amgnet doc(test=document_fix) * fix deepcfd * fix deepcfd * [Doc] Fix document and formulations for cvit (#944) * fix document and formulations * correct doc of Data.batch_transform * update schema for None batch size in INFER config * support batch_size to be set to None where certain data is unnecessary to be batchified * update pre-commit * refine EVAL config schema * Fix eval config (#948) * [Feature] Add loss aggregator to saving/loading process (#949) * fix document and formulations * correct doc of Data.batch_transform * update schema for None batch size in INFER config * support batch_size to be set to None where certain data is unnecessary to be batchified * update pre-commit * refine EVAL config schema * save&load state_dict for loss aggregator * [Doc] Add HKUST badge and remove some codes (#950) * add HKUST icon in cooperation institution * remove unnecessary loss_aggregator in load_pretrain function * resize image * add requests into requirements * Fix typo in mtl/base (#951) * PIDeepONet-LBM (#947) * PIDeepONet-LBM * PIDeepONet-LBM-datasetMountBOS * PIDeepONet-LBM-datasetMountBOS-CUDASet * PIDeepONet-LBM-datasetMountBOS-CUDASet * [PIR] Support pir export and infer (#952) * support export and inference in PIR mode * add validator check * fix solver.predict and device setting (#953) * fix input dtype in shock wave (#954) * [Fix] Fix dtype (#956) * align dtype of input with model parameter * wrap return training loss with dict * update aneurysm zh-cn translation: * [Fix] Adapt code to dy2st mode (#957) * shallow copy input data in expression * shallow copy in ComposedNode.forward * update tempoGAN code linenumber * update code * [Example] Add spinn on helmholtz equation (#958) * update spinn code(WIP) * update code(l2err=0.089) * update SPINN helmholtz3d * update pretraind model url(TRAIN.nc=64) * add spinn doc * refine code and docs * update * update docs * update supports information * update code and doc * refine arch code * Fix return type in examples/tempoGAN/functions.py for tempoGAN (#963) * [Add]add paddle version code of IJACA 2024 (#959) * [Add]add paddle version code of IJACA 2024 * update README.txt * update command of README.txt and some hints * [Doc] Update guidance of development (#965) * update SPINN url * update url * annotate latex which may occur error when latex font is not installed * add mtl submodule to loss.__all__ * update doc * update pre-commit guidance * update synchronization of upstream guidance * [Doc] Update url (#966) * update SPINN url * update url * annotate latex which may occur error when latex font is not installed * add mtl submodule to loss.__all__ * update doc * update pre-commit guidance * update synchronization of upstream guidance * update docs * update batch size computation * rename IJACA -> IJCAI * update description * remove redundant import * 整理代码并准备提交 * 整理代码并准备提交 * 整理代码并准备提交 * perovskite * 使用 Git LFS 跟踪大文件 * Remove large files from version control * Remove LFS tracking and update .gitattributes * 提交在 new_feature_branch 上的更改 * Your commit message * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Remove MLP folder from Git tracking * 修复 MLP_LI 文件中的尾随空格 * Save local changes to mkdocs.yml * Update MLP_LI documentation and results images * 整理代码并提交到 dev_model 分支 * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * 整理代码，提交新增和修改的文件 * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop * Resolve merge conflicts and merge upstream develop --------- Co-authored-by: HydrogenSulfate <490868991@qq.com> Co-authored-by: megemini <megemini@outlook.com> Co-authored-by: ooo oo <106524776+ooooo-create@users.noreply.github.com> Co-authored-by: Tianchi <62602289+DUCH714@users.noreply.github.com> Co-authored-by: WG <39621324+wangguan1995@users.noreply.github.com> Co-authored-by: wangguan <772359200@qq.com> Co-authored-by: xusuyong <107761330+xusuyong@users.noreply.github.com> Co-authored-by: zzm <95690929+zhiminzhang0830@users.noreply.github.com> Co-authored-by: lijialin03 <124568209+lijialin03@users.noreply.github.com> Co-authored-by: Turingg <732153168@qq.com> Co-authored-by: Turingg <117662096+Turingg@users.noreply.github.com> Co-authored-by: Tao Luo <luotao02@baidu.com> Co-authored-by: 张春乔 <83450930+Liyulingyue@users.noreply.github.com> Co-authored-by: AyaseNana <49900969+NKNaN@users.noreply.github.com> Co-authored-by: Wang Xin <xinwang614@gmail.com> Co-authored-by: GGBond8488 <33050871+GGBond8488@users.noreply.github.com> Co-authored-by: liaoxin2 <136409501+liaoxin2@users.noreply.github.com> Co-authored-by: smallpoxscattered <116335664+smallpoxscattered@users.noreply.github.com> Co-authored-by: hyDONG <116695878+1want2sleep@users.noreply.github.com> Co-authored-by: krp <2934631798@qq.com> Co-authored-by: Wu Fei <72655761+wufei2@users.noreply.github.com> Co-authored-by: MayYouBeProsperous <ljmhz@outlook.com> Co-authored-by: WoWYoYLoL <76137105+WoWYoYLoL@users.noreply.github.com> Co-authored-by: gmm <38800877+mmglove@users.noreply.github.com> Co-authored-by: Xiaoxu Chen <chenxx_id@163.com> Co-authored-by: yangchanghui <71805205+Yang-Changhui@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: KennyNH <63087259+KennyNH@users.noreply.github.com> Co-authored-by: KaiCHEN-HT <96469292+KaiCHEN-HT@users.noreply.github.com>

add-neuraloperator

273d4b2

paddle-bot bot added the contributor label Apr 25, 2024

Yang-Changhui and others added 2 commits April 25, 2024 11:05

add-neuraloperator

f0b900e

Merge branch 'develop' into add_neuraloperator

f0760a7

zhiminzhang0830 reviewed Apr 28, 2024

View reviewed changes

Yang-Changhui and others added 7 commits April 29, 2024 11:47

add-neuraloperator

5c59594

add-neuralopertor

55e5b14

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

34009e8

…/PaddleScience into add_neuraloperator

add-neuraloperator

0a1cde8

add-neuraloperator

99fbd35

add-neuraloperator

fd8c49f

Merge branch 'develop' into add_neuraloperator

92db31c

zhiminzhang0830 reviewed May 10, 2024

View reviewed changes

Yang-Changhui and others added 7 commits May 10, 2024 20:05

Merge branch 'develop' into add_neuraloperator

1be2a63

add-neuraloperator

a8c5526

add-neuraloperator

11c50fd

Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleScience…

9dc7917

… into add_neuraloperator

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

a48e8fb

…/PaddleScience into add_neuraloperator

add-neuraloperator

b1df8c4

Merge branch 'develop' into add_neuraloperator

df747a9

Yang-Changhui mentioned this pull request May 10, 2024

[WeeklyReports] 2024.04.19~2024.05.10 周报汇总 PFCCLab/Camp#252

Closed

29 tasks

zhiminzhang0830 reviewed May 11, 2024

View reviewed changes

Yang-Changhui and others added 6 commits May 13, 2024 11:48

add-neuraloperator

2a4d0da

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

c91d92f

…/PaddleScience into add_neuraloperator

Merge branch 'develop' into add_neuraloperator

5e5ad68

add-neuraloperator

750bb7d

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

cb76494

…/PaddleScience into add_neuraloperator

Merge branch 'develop' into add_neuraloperator

9dcd49a

Yang-Changhui mentioned this pull request May 25, 2024

[WeeklyReports] 2024.05.11~2024.05.24 周报汇总 PFCCLab/Camp#280

Closed

29 tasks

zhiminzhang0830 reviewed May 26, 2024

View reviewed changes

Yang-Changhui and others added 3 commits May 26, 2024 14:47

add-neuraloperator

560592d

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

f1b197f

…/PaddleScience into add_neuraloperator

Merge branch 'develop' into add_neuraloperator

60aa2c8

zhiminzhang0830 reviewed May 26, 2024

View reviewed changes

Yang-Changhui added 2 commits May 26, 2024 19:24

add-neuraloperator

8d72bf7

Merge branch 'add_neuraloperator' of https://github.com/Yang-Changhui…

7b819fc

…/PaddleScience into add_neuraloperator

zhiminzhang0830 approved these changes May 27, 2024

View reviewed changes

zhiminzhang0830 merged commit aa963b8 into PaddlePaddle:develop May 27, 2024

Yang-Changhui mentioned this pull request Jun 11, 2024

WAVE SUMMIT+2024上半年飞桨开源之星评选-信息征集 PaddlePaddle/community#892

Closed

		padded = F.pad(x, padding, mode="constant")

		output_shape = padded.shape[2:]



		def _contract_dense_trick(x, weight_real, weight_imag, separable=False, dhconv=True):
		# the same as above function, but do the complex multiplication manually to avoid the einsum bug in paddle



		class SphericalConv(nn.Layer):
		"""Spherical Convolution, base class for the SFNO [1]_

		solver.export(input_spec, cfg.INFER.export_path)


		# 使用静态图推理出错

Conversation

Yang-Changhui commented Apr 25, 2024

PR types

PR changes

Describe

Uh oh!

paddle-bot bot commented Apr 25, 2024

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

zhiminzhang0830 May 10, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Yang-Changhui commented May 20, 2024

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

zhiminzhang0830 May 10, 2024 •

edited

Loading