机器学习 SGD Momentum RMSprop Adam 优化器对比(pytorch)

下面直接给出代码, 中间带有我个人的注释:

#  -*- coding: utf-8 -*-
# 4种优化器的对比

import torch
import torch.utils.data as Data
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

##优化器的对比

LR = 0.01
BATCH_SIZE = 32
EPOCH = 12



x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim= 1)  #-1 到1 分成1000份, 然后展开成2维
y = x.pow(2) + 0.1 * torch.normal(torch.zeros(*x.size())) # 生成1000份的0向量, + x的平方
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset = torch_dataset, batch_size = BATCH_SIZE)


class Net(torch.nn.Module):
	def __init__(self):
		super(Net, self).__init__()
		self.hidden = torch.nn.Linear(1, 20)
		self.predict = torch.nn.Linear(20, 1)


	def forward(self, x):
		x = F.relu(self.hidden(x))
		x = self.predict(x)
		return x




net_SGD =   Net()
net_Momentum =    Net()
net_RMSprop =    Net()
net_adam =    Net()
nets = [net_SGD, net_Momentum, net_RMSprop, net_adam]

opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr = LR)
opt_Momentum = torch.optim.SGD(net_SGD.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 = [[], [],[],[]]

for epoch in range(EPOCH):
	print(epoch)
	for step, (batch_x, batch_y) in enumerate(loader):
		b_x= Variable(batch_x)
		b_y = Variable(batch_y)

		for net, opt, l_his in zip(nets, optimizers, losses_his):
			output = net(b_x)
			loss = loss_func(output, b_y)
			opt.zero_grad()
			loss.backward()
			opt.step()
			l_his.append(loss.item()) # 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()

# optimizer = torch.optim.SGD()
# torch.optim.

结果如下