<p>在玩了一段时间的超参数、修改网络和更改优化器(遵循<a href="http://karpathy.github.io/2019/04/25/recipe/" rel="nofollow noreferrer">this</a>极好的配方)之后,我最终将行<code>optimizer = torch.optim.SGD(net.parameters(), lr = learningrate)</code>更改为<code>optimizer = torch.optim.Adam(net.parameters())</code>(使用了<a href="https://pytorch.org/docs/stable/optim.html#torch.optim.Adam" rel="nofollow noreferrer">default</a>优化器参数),运行了100个时代,批大小等于1。你知道吗</p>
<p>使用了以下代码(仅在CPU上测试):</p>
<pre><code>import torch
import torch.nn as nn
from torch.utils import data
import numpy as np
import matplotlib.pyplot as plt
# for reproducibility
torch.manual_seed(0)
np.random.seed(0)
class Dataset(data.Dataset):
def __init__(self, init, end, n):
self.n = n
self.x = np.random.rand(self.n, 1) * (end - init) + init
self.y = np.sin(self.x)
def __len__(self):
return self.n
def __getitem__(self, idx):
x = self.x[idx, np.newaxis]
y = self.y[idx, np.newaxis]
return torch.Tensor(x), torch.Tensor(y)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.model = nn.Sequential(
nn.Linear(1, 20),
nn.Sigmoid(),
nn.Linear(20, 50),
nn.Sigmoid(),
nn.Linear(50, 50),
nn.Sigmoid(),
nn.Linear(50, 1)
)
def forward(self, x):
x = self.model(x)
return x
def train(net, trainloader, valloader, n_epochs):
loss = nn.MSELoss()
# Switch the two following lines and run the code
# optimizer = torch.optim.SGD(net.parameters(), lr = 0.0001)
optimizer = torch.optim.Adam(net.parameters())
for epoch in range(n_epochs):
net.train()
for x, y in trainloader:
optimizer.zero_grad()
outputs = net(x).view(-1)
error = loss(outputs, y)
error.backward()
optimizer.step()
net.eval()
total_loss = 0
for x, y in valloader:
outputs = net(x)
error = loss(outputs, y)
total_loss += error.data
print('Val loss for epoch', epoch, 'is', total_loss / len(valloader) )
net.eval()
f, (ax1, ax2) = plt.subplots(1, 2, sharey=True)
def plot_result(ax, dataloader):
out, xx, yy = [], [], []
for x, y in dataloader:
out.append(net(x))
xx.append(x)
yy.append(y)
out = torch.cat(out, dim=0).detach().numpy().reshape(-1)
xx = torch.cat(xx, dim=0).numpy().reshape(-1)
yy = torch.cat(yy, dim=0).numpy().reshape(-1)
ax.scatter(xx, yy, facecolor='green')
ax.scatter(xx, out, facecolor='red')
xx = np.linspace(0.0, 3.14159*2, 1000)
ax.plot(xx, np.sin(xx), color='green')
plot_result(ax1, trainloader)
plot_result(ax2, valloader)
plt.show()
train_dataset = Dataset(0.0, 3.14159*2, 100)
val_dataset = Dataset(0.0, 3.14159*2, 30)
params = {'batch_size': 1,
'shuffle': True,
'num_workers': 4}
trainloader = data.DataLoader(train_dataset, **params)
valloader = data.DataLoader(val_dataset, **params)
net = Net()
losslist = train(net, trainloader, valloader, n_epochs = 100)
</code></pre>
<p>Adam优化器的结果:
<a href="https://i.stack.imgur.com/5i3Qy.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/5i3Qy.png" alt="enter image description here"/></a></p>
<p>SGD优化器的结果:
<a href="https://i.stack.imgur.com/PfSLr.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/PfSLr.png" alt="enter image description here"/></a></p>