1 class TrainingDataset(Dataset):
 2 
 3     def __init__(self, X, Y_, transform=None, target_transform=None):
 4         self.__X = X
 5         self.__Y_ = Y_
 6         self.__transform = transform
 7         self.__target_transform = target_transform 
 8 
 9 
10     def __len__(self):
11         return len(self.__X)
12 
13 
14     def __getitem__(self, idx):
15         x = self.__X[idx]
16         y_ = self.__Y_[idx]
17         if self.__transform:
18             x = self.__transform(x)
19         if self.__target_transform:
20             y_ = self.__target_transform(y_)
21         return x, y_

关于DataLoader, 作为数据集封装, 将数据集Dataset封装为可迭代对象. 示例如下,

1 batch_size = 100
2 trainingLoader = DataLoader(trainingData, batch_size=batch_size, shuffle=True)

Part Ⅱ: 模型确立
torch.nn 
torch.nn.Module 
网络模型由基类Module派生, 内部所有操作模块均由命名空间nn提供, 需要实现基本的2个方法, 分别为: __init__、forward. 其中, __init__方法定义操作, forward方法运用操作进行正向计算. 示例如下,

 1 class NeuralNetwork(nn.Module):
 2 
 3     def __init__(self):
 4         super(NeuralNetwork, self).__init__()
 5         self.__linear_tanh_stack = nn.Sequential(
 6             nn.Linear(3, 5),
 7             nn.Tanh(),
 8             nn.Linear(5, 3)
 9         )
10 
11 
12     def forward(self, x):
13         y = self.__linear_tanh_stack(x)
14         return y
15 
16 
17 model = NeuralNetwork()

Part Ⅲ: 损失函数确立
torch.nn 
常见损失函数有: nn.MSELoss(回归任务)、nn.CrossEntropyLoss(多分类任务)等. 示例如下,

1 loss_func = nn.MSELoss(reduction="sum")

Part Ⅳ: 优化器确立
torch.optim 
常见的优化器有: optim.SGD、optim.Adam等. 示例如下,

1 optimizer = optim.Adam(model.parameters(), lr=0.001)

Part Ⅴ: 模型训练及保存
有效整合数据、模型、损失函数及优化器. 注意, 模型参数之梯度默认累积, 每次参数优化需要显式清零. 示例如下,

 1 def train_loop(dataloader, model, loss_func, optimizer):
 2     for batchIdx, (X, Y_) in enumerate(dataloader):
 3         Y = model(X)
 4         loss = loss_func(Y, Y_)
 5 
 6         optimizer.zero_grad()
 7         loss.backward()
 8         optimizer.step()
 9 
10         
11 epoch = 50000
12 for epochIdx in range(epoch):
13     train_loop(trainingLoader, model, loss_func, optimizer)
14 
15 
16 torch.save(model.state_dict(), "model_params.pth")

$$
\begin{equation*}
\left\{
\begin{split}
x &= r + 2g + 3b \\
y &= r^2 + 2g^2 + 3b^2 \\
lv &= -3r - 4g - 5b
\end{split}
\right.
\end{equation*} 
$$
具体实现如下,

  1 import numpy
  2 import torch
  3 from torch import nn
  4 from torch import optim
  5 from torch.utils.data import Dataset, DataLoader
  6 from matplotlib import pyplot as plt
  7 
  8 
  9 numpy.random.seed(1)
 10 torch.manual_seed(3)
 11 
 12 
 13 # 生成training数据
 14 def getData(n=100):
 15     rgbRange = (-1, 1)
 16     r = numpy.random.uniform(*rgbRange, (n, 1))
 17     g = numpy.random.uniform(*rgbRange, (n, 1))
 18     b = numpy.random.uniform(*rgbRange, (n, 1))
 19     x_ = r + 2 * g + 3 * b
 20     y_ = r ** 2 + 2 * g ** 2 + 3 * b ** 2
 21     lv_ = -3 * r - 4 * g - 5 * b
 22     RGB = numpy.hstack((r, g, b))
 23     XYLv_ = numpy.hstack((x_, y_, lv_))
 24     return RGB, XYLv_
 25 
 26 
 27 class TrainingDataset(Dataset):
 28 
 29     def __init__(self, X, Y_, transform=None, target_transform=None):
 30         self.__X = X
 31         self.__Y_ = Y_
 32         self.__transform = transform
 33         self.__target_transform = target_transform 
 34 
 35 
 36     def __len__(self):
 37         return len(self.__X)
 38 
 39 
 40     def __getitem__(self, idx):
 41         x = self.__X[idx]
 42         y_ = self.__Y_[idx]
 43         if self.__transform:
 44             x = self.__transform(x)
 45         if self.__target_transform:
 46             y_ = self.__target_transform(y_)
 47         return x, y_
 48 
 49 
 50 RGB, XYLv_ = getData(1000)
 51 trainingData = TrainingDataset(RGB, XYLv_, torch.Tensor, torch.Tensor)
 52 
 53 batch_size = 100
 54 trainingLoader = DataLoader(trainingData, batch_size=batch_size, shuffle=True)
 55 
 56 
 57 class NeuralNetwork(nn.Module):
 58 
 59     def __init__(self):
 60         super(NeuralNetwork, self).__init__()
 61         self.__linear_tanh_stack = nn.Sequential(
 62             nn.Linear(3, 5),
 63             nn.Tanh(),
 64             nn.Linear(5, 3)
 65         )
 66 
 67 
 68     def forward(self, x):
 69         y = self.__linear_tanh_stack(x)
 70         return y
 71 
 72 
 73 model = NeuralNetwork()
 74 loss_func = nn.MSELoss(reduction="sum")
 75 optimizer = optim.Adam(model.parameters(), lr=0.001)
 76 
 77 
 78 def train_loop(dataloader, model, loss_func, optimizer):
 79     JVal = 0
 80     for batchIdx, (X, Y_) in enumerate(dataloader):
 81         Y = model(X)
 82         loss = loss_func(Y, Y_)
 83 
 84         JVal += loss.item()
 85 
 86         optimizer.zero_grad()
 87         loss.backward()
 88         optimizer.step()
 89 
 90     JVal /= 2
 91     return JVal
 92 
 93 
 94 JPath = list()
 95 epoch = 50000
 96 for epochIdx in range(epoch):
 97     JVal = train_loop(trainingLoader, model, loss_func, optimizer)
 98     print("epoch: {:5d},   JVal = {:.5f}".format(epochIdx, JVal))
 99     JPath.append(JVal)
100 
101 
102 torch.save(model.state_dict(), "model_params.pth")
103 
104 
105 fig = plt.figure(figsize=(6, 4))
106 ax1 = fig.add_subplot(1, 1, 1)
107 
108 ax1.plot(numpy.arange(len(JPath)), JPath, "k.", markersize=1)
109 ax1.plot(0, JPath[0], "go", label="seed")
110 ax1.plot(len(JPath)-1, JPath[-1], "r*", label="solution")
111 
112 ax1.legend()
113 ax1.set(xlabel="$epoch$", ylabel="$JVal$", title="solution-JVal = {:.5f}".format(JPath[-1]))
114 
115 fig.tight_layout()
116 fig.savefig("plot_fig.png", dpi=100)

使用建议
①. 分batch处理训练数据, 可以提升训练初始阶段模型参数收敛速度;
②. 常规优化器推荐Adam, 具备自动步长调节的能力.