Detaillierte Erläuterung des PyTorch-Batch-Trainings und des Optimierervergleichs

import torch 
import torch.utils.data as Data 
 
torch.manual_seed(1) # 设定随机数种子 
 
BATCH_SIZE = 5 
 
x = torch.linspace(1, 10, 10) 
y = torch.linspace(0.5, 5, 10) 
 
# 将数据转换为torch的dataset格式 
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y) 
 
# 将torch_dataset置入Dataloader中 
loader = Data.DataLoader( 
  dataset=torch_dataset, 
  batch_size=BATCH_SIZE, # 批大小 
  # 若dataset中的样本数不能被batch_size整除的话，最后剩余多少就使用多少 
  shuffle=True, # 是否随机打乱顺序 
  num_workers=2, # 多线程读取数据的线程数 
  ) 
 
for epoch in range(3): 
  for step, (batch_x, batch_y) in enumerate(loader): 
    print('Epoch:', epoch, '|Step:', step, '|batch_x:', 
       batch_x.numpy(), '|batch_y', batch_y.numpy()) 
''''' 
shuffle=True 
Epoch: 0 |Step: 0 |batch_x: [ 6. 7. 2. 3. 1.] |batch_y [ 3.  3.5 1.  1.5 0.5] 
Epoch: 0 |Step: 1 |batch_x: [ 9. 10.  4.  8.  5.] |batch_y [ 4.5 5.  2.  4.  2.5] 
Epoch: 1 |Step: 0 |batch_x: [ 3.  4.  2.  9. 10.] |batch_y [ 1.5 2.  1.  4.5 5. ] 
Epoch: 1 |Step: 1 |batch_x: [ 1. 7. 8. 5. 6.] |batch_y [ 0.5 3.5 4.  2.5 3. ] 
Epoch: 2 |Step: 0 |batch_x: [ 3. 9. 2. 6. 7.] |batch_y [ 1.5 4.5 1.  3.  3.5] 
Epoch: 2 |Step: 1 |batch_x: [ 10.  4.  8.  1.  5.] |batch_y [ 5.  2.  4.  0.5 2.5] 
 
shuffle=False 
Epoch: 0 |Step: 0 |batch_x: [ 1. 2. 3. 4. 5.] |batch_y [ 0.5 1.  1.5 2.  2.5] 
Epoch: 0 |Step: 1 |batch_x: [ 6.  7.  8.  9. 10.] |batch_y [ 3.  3.5 4.  4.5 5. ] 
Epoch: 1 |Step: 0 |batch_x: [ 1. 2. 3. 4. 5.] |batch_y [ 0.5 1.  1.5 2.  2.5] 
Epoch: 1 |Step: 1 |batch_x: [ 6.  7.  8.  9. 10.] |batch_y [ 3.  3.5 4.  4.5 5. ] 
Epoch: 2 |Step: 0 |batch_x: [ 1. 2. 3. 4. 5.] |batch_y [ 0.5 1.  1.5 2.  2.5] 
Epoch: 2 |Step: 1 |batch_x: [ 6.  7.  8.  9. 10.] |batch_y [ 3.  3.5 4.  4.5 5. ] 
'''

classtorch.utils.data.TensorDataset(data_tensor, target_tensor)

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) # 设定随机数种子 
 
# 定义超参数 
LR = 0.01 # 学习率 
BATCH_SIZE = 32 # 批大小 
EPOCH = 12 # 迭代次数 
 
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1) 
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size())) 
 
#plt.scatter(x.numpy(), y.numpy()) 
#plt.show() 
 
# 将数据转换为torch的dataset格式 
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y) 
# 将torch_dataset置入Dataloader中 
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, 
             shuffle=True, num_workers=2) 
 
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 
 
# 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] 
 
# 初始化优化器 
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] 
 
# 定义损失函数 
loss_function = torch.nn.MSELoss() 
losses_history = [[], [], [], []] # 记录training时不同神经网络的loss值 
 
for epoch in range(EPOCH): 
  print('Epoch:', epoch + 1, 'Training...') 
  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_history): 
      output = net(b_x) 
      loss = loss_function(output, b_y) 
      opt.zero_grad() 
      loss.backward() 
      opt.step() 
      l_his.append(loss.data[0]) 
 
labels = ['SGD', 'Momentum', 'RMSprop', 'Adam'] 
 
for i, l_his in enumerate(losses_history): 
  plt.plot(l_his, label=labels[i]) 
plt.legend(loc='best') 
plt.xlabel('Steps') 
plt.ylabel('Loss') 
plt.ylim((0, 0.2)) 
plt.show()

x = [1, 2, 3] 
y = [4, 5, 6] 
z = [7, 8, 9] 
xyz = zip(x, y, z) 
print xyz 
[(1, 4, 7), (2, 5, 8), (3, 6, 9)] 
 
x = [1, 2, 3] 
x = zip(x) 
print x 
[(1,), (2,), (3,)] 
 
x = [1, 2, 3] 
y = [4, 5, 6, 7] 
xy = zip(x, y) 
print xy 
[(1, 4), (2, 5), (3, 6)]