import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
import matplotlib.pyplot as plt
import torch.utils.data as Data
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12
# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 300), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
torch_dataset = Data.TensorDataset(x,y)
loader = Data.DataLoader(
dataset=torch_dataset,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=2
)
class Net(nn.Module):
def __init__(self):
super(Net,self).__init__()
self.hidden = nn.Linear(1,20)
self.prediction = nn.Linear(20,1)
def forward(self, x):
x = F.relu(self.hidden(x))
x = self.prediction(x)
return x
def main():
net_SGD = Net()
net_Momentum = Net()
net_Adam = Net()
nets = [net_SGD, net_Momentum, net_Adam]
opt_SGD = optim.SGD(net_SGD.parameters(), lr=LR)
opt_Momentum = optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.9)
opt_Adam = optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
optimizers = [opt_SGD, opt_Momentum, opt_Adam]
loss_func = nn.MSELoss()
losses_his = [[], [], []]
#training
for epoch in range(EPOCH):
print('EPOCH:',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):
out = net(b_x)
loss = loss_func(out,b_y)
opt.zero_grad()
loss.backward()
opt.step()
l_his.append(loss.item())
labels = ['SGD', 'Momentum', '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()
if __name__ == '__main__':
main()
结果图: