文件列表:

LICENSE (1068, 2020-03-17)
__init__.py (87, 2020-03-17)
nn (0, 2020-03-17)
nn\__init__.py (47, 2020-03-17)
nn\functional (0, 2020-03-17)
nn\functional\__init__.py (50, 2020-03-17)
nn\functional\interpolation.py (6697, 2020-03-17)
nn\functional\utils.py (3117, 2020-03-17)
nn\modules (0, 2020-03-17)
nn\modules\FD.py (9110, 2020-03-17)
nn\modules\Interpolation.py (6422, 2020-03-17)
nn\modules\MK.py (3100, 2020-03-17)
nn\modules\__init__.py (65, 2020-03-17)
optim (0, 2020-03-17)
optim\NFI.py (8762, 2020-03-17)
optim\PGManager.py (11963, 2020-03-17)
optim\__init__.py (218, 2020-03-17)
pdetools (0, 2020-03-17)
pdetools\__init__.py (131, 2020-03-17)
pdetools\example (0, 2020-03-17)
pdetools\example\__init__.py (20, 2020-03-17)
pdetools\example\burgers2d.py (7171, 2020-03-17)
pdetools\example\cde2d.py (8789, 2020-03-17)
pdetools\example\cdr2d.py (5442, 2020-03-17)
pdetools\example\rd2d.py (5207, 2020-03-17)
pdetools\init.py (1532, 2020-03-17)
pdetools\spectral.py (4730, 2020-03-17)
pdetools\stepper.py (4659, 2020-03-17)
pdetools\upwind.py (2691, 2020-03-17)
test (0, 2020-03-17)
test\fd_test.py (2738, 2020-03-17)
test\fdproj_test.py (325, 2020-03-17)
test\interp_test2d.py (3702, 2020-03-17)
test\interp_test3d.py (4428, 2020-03-17)
test\mk_test.py (1455, 2020-03-17)
test\modules_test2d.py (3463, 2020-03-17)
test\modules_test3d.py (6228, 2020-03-17)
test\optim_quickstart.py (8139, 2020-03-17)
... ...

# aTEAM **A** py**T**orch **E**xtension for **A**pplied **M**athematics This version is compatible with pytorch (1.0.1) and later. You can create a conda environment for pytorch1: ``` conda create -n torch1 python=3 jupyter source activate torch1 conda install pytorch=1 torchvision cudatoolkit=9.2 -c pytorch # or conda install pytorch-cpu=1 -c pytorch ``` ## Some code maybe useful to you (News: add optim QuickStart) - aTEAM.optim.NumpyFuntionInterface: This function enable us to optimize pytorch modules with external optimizer such as scipy.optimize.lbfgsb.fmin_l_bfgs_b, see test/optim_quickstart.py - aTEAM.nn.modules.MK: [Moment matrix](https://arxiv.org/abs/1710.09668) & convolution kernel convertor: aTEAM.nn.modules.MK.M2K, aTEAM.nn.module.MK.K2M - aTEAM.nn.modules.Interpolation: Lagrange interpolation in a n-dimensional box: aTEAM.nn.modules.Interpolation.LagrangeInterp, aTEAM.nn.modules.Interpolation.LagrangeInterpFixInputs - aTEAM.nn.functional.utils.tensordot: It is similar to numpy.tensordot For more usages pls refer to aTEAM/test/*.py # PDE-Net aTEAM is a basic library for PDE-Net & PDE-Net 2.0[(source code)](https://github.com/ZichaoLong/PDE-Net): - [PDE-Net: Learning PDEs from Data](https://arxiv.org/abs/1710.09668)[(ICML 2018)](https://icml.cc/Conferences/2018)
[Long Zichao](https://scholar.google.com/citations?user=0KXcwnkAAAAJ&hl=zh-CN), [Lu Yiping](https://web.stanford.edu/~yplu/), [Ma Xianzhong](https://www.researchgate.net/profile/Xianzhong_Ma), [Dong Bin](http://bicmr.pku.edu.cn/~dongbin) - [PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network](https://arxiv.org/abs/1812.04426)
[Long Zichao](https://scholar.google.com/citations?user=0KXcwnkAAAAJ&hl=zh-CN), [Lu Yiping](https://web.stanford.edu/~yplu/), [Dong Bin](http://bicmr.pku.edu.cn/~dongbin) If you find this code useful for your research then please cite ``` @inproceedings{long2018pdeI, title={PDE-Net: Learning PDEs from Data}, author={Long, Zichao and Lu, Yiping and Ma, Xianzhong and Dong, Bin}, booktitle={International Conference on Machine Learning}, pages={3214--3222}, year={2018} } @article{long2018pdeII, title={PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network}, author={Long, Zichao and Lu, Yiping and Dong, Bin}, journal={arXiv preprint arXiv:1812.04426}, year={2018} } ```

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：