一些知识
torch.manual_seed
设定生成随机数的种子,并返回一个torch._C.Generator 对象.
torch.manual_seed(seed)
torch.unsqueeze
返回一个新的张量,对输入的制定位置插入维度 1
注意: 返回张量与输入张量共享内存,所以改变其中一个的内容会改变另一个。
>>> x = torch.Tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
1 2 3 4
[torch.FloatTensor of size 1x4]
>>> torch.unsqueeze(x, 1)
1
2
3
4
[torch.FloatTensor of size 4x1]
代码
import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
torch.manual_seed(1)
# 超参数
LR = 0.01 # 学习率
BATCH_SIZE = 32 # 一次批训练的数据多少
EPOCH = 12 # 迭代多少次
# 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 显示数据
plt.scatter(x.numpy(), y.numpy())
plt.show()
# 批训练 data loader
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(
dataset=torch_dataset,
batch_size=BATCH_SIZE,
shuffle=True, # 是否打乱数据
num_workers=0,
)
# 每一个优化器优化一个NN
# 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]
# 创建不同的优化器,训练不同的网络
# 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() # 损失函数 计算误差
losses_his = [[], [], [], []] # 记录 training 时不同神经网络的 loss
# 训练
for epoch in range(EPOCH):
print('Epoch: ', epoch)
for step, (b_x, b_y) in enumerate(loader):
# 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.numpy()) # 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()
结果
原始伪数据
对比结果