使用Mindspore拟合f(x)=a*sin(x)+b这类函数

最新推荐文章于 2024-09-13 19:41:31 发布

小乐快乐

最新推荐文章于 2024-09-13 19:41:31 发布

阅读量149

点赞数

文章标签： python 深度学习自然语言处理

本文链接：https://blog.csdn.net/weixin_45666880/article/details/118444425

版权

根据mindspore线性拟合官方案例改编而成

f(x)=w * sin(x) + b，下面脚本展示将以 f(x)=2 * sin(x) +3为实例。

#导入所需的工具包

import numpy as np

from mindspore import dataset as ds

from mindspore.common.initializer import Normal

from mindspore import nn

from mindspore.train import Model

from mindspore.train.callback import LossMonitor

from mindspore import context

#确定运行的硬件平台

context.set_context(mode=context.GRAPH_MODE, device_target="CPU")
#设定要拟合的函数

def get_data(num, w=2.0, b=3.0):

    # f(x)=w * sin(x) + b

    # f(x)=2 * sin(x) +3

    for i in range(num):

        x = np.random.uniform(-np.pi, np.pi)

        noise = np.random.normal(0, 1)

        y = w * np.sin(x) + b + noise

        yield np.array([np.sin(x)]).astype(np.float32), np.array([y]).astype(np.float32)
#初始化开始的参数

class LinearNet(nn.Cell):

    def __init__(self):

        super(LinearNet, self).__init__()

        self.fc = nn.Dense(1, 1, Normal(0.02), Normal(0.02))

    def construct(self, x):

        x = self.f
#开始拟合，设定初始化超参数。

if __name__ == "__main__":

    num_data = 1600

    batch_size = 16

    repeat_size = 1

    lr = 0.005

    momentum = 0.9



    net = LinearNet()

    net_loss = nn.loss.MSELoss()

    opt = nn.Momentum(net.trainable_params(), lr, momentum)

    model = Model(net, net_loss, opt)



    ds_train = create_dataset(num_data, batch_size=batch_size, repeat_size=repeat_size)

    model.train(1, ds_train, callbacks=LossMonitor(), dataset_sink_mode=False)



    print(net.trainable_params()[0], "\n%s" % net.trainable_params()[1])