torch.optim is a package implementing various optimization algorithms. Most commonly used methods are already supported, and the interface is general enough, so that more sophisticated ones can be also easily integrated in the future..
更多可以查看官网 :
> PyTorch 官网
载入数据
编造一些伪数据用于实验.
import torch
import torch.utils.data as Data
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt
torch.manual_seed(1) # reproducible
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12
# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
# plot dataset
plt.scatter(x.numpy(), y.numpy())
plt.show()
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)
优化神经网络
为了对比每一种优化器, 我们给他们各自创建一个神经网络, 但这个神经网络都来自同一个 Net 形式.
# 默认的 network 形式
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
# 为每个优化器创建一个 net
net_SGD = Net()
net_Momentum = Net()
net_RMSprop = Net()
net_Adam = Net()
nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]
Optimizer
接下来在创建不同的优化器, 用来训练不同的网络. 并创建一个 loss_func 用来计算误差.
几种常见的优化器, SGD, Momentum, RMSprop, Adam.
# different optimizers
opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr=LR)
opt_Momentum = torch.optim.SGD(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=(0.9, 0.99))
optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]
loss_func = torch.nn.MSELoss()
losses_his = [[], [], [], []] # 记录 training 时不同神经网络的 loss
结果
训练和 loss 画图.
for epoch in range(EPOCH):
print('Epoch: ', epoch)
for step, (batch_x, batch_y) in enumerate(loader):
b_x = Variable(batch_x) # 务必要用 Variable 包一下
b_y = Variable(batch_y)
# 对每个优化器, 优化属于他的神经网络
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[0]) # loss recoder
image
SGD 是最普通的优化器, 也可以说没有加速效果, 而 Momentum 是 SGD 的改良版, 它加入了动量原则.
后面的 RMSprop 又是 Momentum 的升级版. 而 Adam 又是 RMSprop 的升级版.
不过从这个结果中看到, Adam 的效果似乎比 RMSprop 要差一点. 所以说并不是越先进的优化器, 结果越佳.
在试验中可以尝试不同的优化器, 找到那个最适合的数据/网络的优化器.
