Pytorch学习（九）---- 优化器

莫烦python视频学习笔记 视频链接https://www.bilibili.com/video/BV1Vx411j7kT?from=search&seid=3065687802317837578

优化器学习

代码：

import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
# import os 这里是为了防止报错加的

# hyper parameters 超参数
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
# plot
plt.scatter(x.numpy(), y.numpy())
plt.show()

torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)

# 默认神将网络框架
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)  # hidden layer
        self.predict = torch.nn.Linear(20, 1)  # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))  # activation function for hidden layer
        x = self.predict(x)  # linear output
        return x

# different nets
if __name__ == '__main__':
    net_SGD = Net()
    net_Momentum = Net()
    net_RMSprop = Net()
    net_Adam = Net()
    net = [net_SGD, net_Momentum, net_RMSprop, net_Adam]
    # 将四个神经网络放入一个list中，方便后面取出进行训练
    opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr=LR)
    opt_Momentum = torch.optim.Momentum(net_Momentum.parameters(), lr=LR, momentum=0.8)
    opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(), lr=LR, alpha=0.9)
    opt_Adam = torch.optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.8, 0.99))
    optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

    loss_func = torch.nn.MSELoss()
    loss_his = [[], [], [], []]        # record loss

    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        for step, (b_x, b_y) in enumerate(loader):  # for each training step
            for net, opt, l_his in zip(nets, optimizers, losses_his):
                output = net(b_x)  # get output for every net
                loss = loss_func(output, b_y)  # compute loss for every net
                opt.zero_grad()  # clear gradients for next train
                loss.backward()  # backpropagation, compute gradients
                opt.step()  # apply gradients
                l_his.append(loss.data.numpy())  # loss recoder

    labels = ['SGD', 'Momentum', 'RMSprop', 'Adam']
    for i, l_his in enumerate(losses_his):
        plt.plot(l_his, label=labels[i])
    plt.legend(loc='best')
    plt.xlabel('Steps')
    plt.ylabel('Loss')
    plt.ylim((0, 0.2))
    plt.show()

这一节学习失败！ 代码运行中一直有以下的报错，还没有找到解决方法，先放在这吧！ 后面解决了再附上结果图。

AttributeError: module 'torch.optim' has no attribute 'Momentum'