这里用torch 做一个最简单的测试
目标就是我们用torch 建立一个一层的网络，然后拟合一组可以回归的数据
import torch from torch.autograd import Variable import torch.nn.functional as F import matplotlib.pyplot as plt x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) y = x.pow(2) + 0.2*torch.rand(x.size()) x, y = Variable(x), Variable(y)
这里我们先早出来假数据，这里需要注意的是，最新版本的torch已经不需要variable了
接着我们来搭建我们的网络
class Net(torch.nn.Module): def __init__(self, n_feature, n_hidden, n_output): super(Net, self).__init__() self.hidden = torch.nn.Linear(n_feature, n_hidden) self.predict = torch.nn.Linear(n_hidden, n_output) # 前向传播 def forward(self, x): x = F.relu(self.hidden(x)) x = self.predict(x) return x
我们做了个 1-10-1这样的单隐藏层的网络
net = Net(n_feature=1, n_hidden=10, n_output=1) print(net) # define optimizer optimizer = torch.optim.SGD(net.parameters(), lr=0.5) loss_func = torch.nn.MSELoss()
接着我们选SGD来优化，选MSE做loss function
开始训练
plt.ion() # begin training for t in range(200): prediction = net(x) loss = loss_func(prediction, y) # must be (1. nn output, 2. target) optimizer.zero_grad() # clear gradients for next train loss.backward() # backpropagation, compute gradients optimizer.step() # apply gradients if t % 5 == 0: plt.cla() plt.scatter(x.data.numpy(), y.data.numpy()) plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5) plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'}) plt.pause(0.1) plt.ioff() plt.show()
大概效果是这样
