Mac系统安装 deepxde +VS code + pytorch

万俟修诚
2023-12-01

deepxde 在Mac系统安装和学习笔记系列

因为换了苹果电脑MacBook Pro,所以软件都需要重新安装,记录一下安装过程。

我的配置是python+VS Code。

打开终端,直接按住command+空格键,输入终端就可以打开了。

1. deepxde 安装

首先 输入

python3 --version

查看python版本,我的是Python 3.9.13
然后 输入

python3 -m pip -V

查看自己的pip版本,我的是

pip 22.0.4 from /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pip (python 3.9)

安装deepxde

// Install deepxde
pip3 install deepxde

2. deepxde 使用pytorch

deepxde 默认使用tensorflow.compat.v1
因为我想使用pytorch,所以需要更换。

方法

打开终端,依次运行下面的代码

cd .deepxde
open config.json

然后修改config.json就可以了,改为

{"backend": "pytorch"}

3. deepxde例子

python 代码(pytorch)- 求解ODE方程的例子
代码是copy的lulu老师的。在github上有很多代码,lulu老师网页和代码网页如下:

https://github.com/lululxvi
https://deepxde.readthedocs.io/en/latest/demos/pinn_forward/ode.system.html
"""Backend supported: tensorflow.compat.v1, tensorflow, pytorch, jax, paddle"""
import deepxde as dde
import numpy as np


def ode_system(x, y):
    """ODE system.
    dy1/dx = y2
    dy2/dx = -y1
    """
    # Most backends
    y1, y2 = y[:, 0:1], y[:, 1:]
    dy1_x = dde.grad.jacobian(y, x, i=0)
    dy2_x = dde.grad.jacobian(y, x, i=1)
    # Backend jax
    # y_val, y_fn = y
    # y1, y2 = y_val[:, 0:1], y_val[:, 1:]
    # dy1_x, _ = dde.grad.jacobian(y, x, i=0)
    # dy2_x, _ = dde.grad.jacobian(y, x, i=1)
    return [dy1_x - y2, dy2_x + y1]


def boundary(_, on_initial):
    return on_initial


def func(x):
    """
    y1 = sin(x)
    y2 = cos(x)
    """
    return np.hstack((np.sin(x), np.cos(x)))


geom = dde.geometry.TimeDomain(0, 10)
ic1 = dde.icbc.IC(geom, lambda x: 0, boundary, component=0)
ic2 = dde.icbc.IC(geom, lambda x: 1, boundary, component=1)
data = dde.data.PDE(geom, ode_system, [ic1, ic2], 35, 2, solution=func, num_test=100)

layer_size = [1] + [50] * 3 + [2]
activation = "tanh"
initializer = "Glorot uniform"
net = dde.nn.FNN(layer_size, activation, initializer)

model = dde.Model(data, net)
model.compile("adam", lr=0.001, metrics=["l2 relative error"])
losshistory, train_state = model.train(iterations=20000)

dde.saveplot(losshistory, train_state, issave=True, isplot=True)
 类似资料: