用Sequential快速搭建pytorch神经网络
用Sequential快速搭建pytorch神经网络
在pytorch实现回归一文中,搭建神经网络分为两步,首先确定每层结构,然后规定数据流向。
以下代码用Sequential类一步快速搭建神经网络:
import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt
import numpy
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)
y = x.pow(2) + torch.rand(x.size()) * 0.2
x = Variable(x)
y = Variable(y)
# plt.scatter(x.data.numpy(), y.data.numpy())
# plt.show()
class Net(torch.nn.Module):
def __init__(self, n_input, n_hidden, n_output):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(n_input, n_hidden)
self.l2 = torch.nn.Linear(n_hidden, n_output)
def forward(self, x):
x = F.relu(self.l1(x))
x = self.l2(x)
return x
net1 = Net(1, 10, 1)
net2 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
plt.ion()
plt.show()
optimizer = torch.optim.SGD(net2.parameters(), lr=0.2)
loss_func = torch.nn.MSELoss()
for t in range(2000):
prediction = net2(x) # result from neural network
loss = loss_func(prediction, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
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) # color of line = r,width of line = 5
plt.text(0.5, 0, 'Loss=%.4f' % loss.data, fontdict={'size': 20, 'color': 'red'})
plt.pause(0.1)
plt.ioff()
plt.show()
输出结果:
第34行的net2即使用Sequential搭建神经网络的过程,其他代码与pytorch实现回归文中代码相同。
最后应用此网络的输出效果与pytorch实现回归的结果一致。
只需在Sequential类中依次输入每一层结构,即可完成搭建。