上一篇文章PyTorch深度学习实践概论笔记5-用pytorch实现线性回归课后练习2老师推荐从pytorch官方教程查看更多的例子，上一篇文章字数过多，于是分成2部分。
目录
2.1 PyTorch: Tensors and autograd
2.2 PyTorch: Defining new autograd functions
3.3 PyTorch: Custom nn Modules
3.4 PyTorch: Control Flow + Weight Sharing
NOTE
This is one of our older PyTorch tutorials. You can view our latest beginner content in Learn the Basics.
This tutorial introduces the fundamental concepts of PyTorch through self-contained examples.
【请注意
这是我们的一个旧的PyTorch教程。您可以在学习基础知识中查看我们最新的初学者内容。
本教程通过自包含的示例介绍了PyTorch的基本概念。】
At its core, PyTorch provides two main features:
- An n-dimensional Tensor, similar to numpy but can run on GPUs
- Automatic differentiation for building and training neural networks
【在其核心，PyTorch提供了两个主要特性:
- 一个n维张量，类似于numpy，但可以在gpu上运行
- 自动区分建立和训练神经网络】
We will use a problem of fitting \(y=\sin(x)\) with a third order polynomial as our running example. The network will have four parameters, and will be trained with gradient descent to fit random data by minimizing the Euclidean distance between the network output and the true output.
【我们将使用一个三阶多项式拟合(y= sin(x))的问题作为我们的运行示例。该网络将有四个参数，并将通过梯度下降训练，通过最小化网络输出和真实输出之间的欧氏距离来拟合随机数据。】
NOTE
You can browse the individual examples at the end of this page.
【请注意
您可以在本页末尾浏览各个示例。】
1 Tensors
1.1 warm-up:numpy
Before introducing PyTorch, we will first implement the network using numpy.
【在引入PyTorch之前，我们将首先使用numpy实现网络。】
Numpy provides an n-dimensional array object, and many functions for manipulating these arrays. Numpy is a generic framework for scientific computing; it does not know anything about computation graphs, or deep learning, or gradients. However we can easily use numpy to fit a third order polynomial to sine function by manually implementing the forward and backward passes through the network using numpy operations:
【Numpy提供了一个n维数组对象，以及许多用于操作这些数组的函数。Numpy是科学计算的通用框架；它不知道任何关于计算图或深度学习或梯度的东西。然而，我们可以很容易地使用numpy来拟合三阶多项式到正弦函数，通过使用numpy操作手动实现正向和向后通过网络：】
这一部分介绍np.linspace()的使用，如果熟悉请直接跳过。
np.linspace主要用来创建等差数列。
一般形式为：
numpy.linspace(start, stop, num=50, endpoint=True, retstep=False, dtype=None, axis=0)Returns num evenly spaced samples, calculated over the interval [start, stop].
【返回的是 [start, stop]之间的均匀分布】
The endpoint of the interval can optionally be excluded.【区间的端点可以被选择性地排除】
参数：
start：返回样本数据开始点
stop：返回样本数据结束点
num：生成的样本数据量，默认为50
endpoint：True则包含stop端点；False则不包含stop端点
retstep：If True, return (samples, step), where step is the spacing between samples.(即如果为True则结果会给出数据间隔)
dtype：输出数组类型
axis：0(默认)或-1例子：
np.linspace(2.0, 3.0, num=5) #array([ 2. , 2.25, 2.5 , 2.75, 3. ]) np.linspace(2.0, 3.0, num=5, endpoint=False) #array([ 2. , 2.2, 2.4, 2.6, 2.8]) np.linspace(2.0, 3.0, num=5, retstep=True) #(array([ 2. , 2.25, 2.5 , 2.75, 3. ]), 0.25)
接着讲解：
# -*- coding: utf-8 -*-
import numpy as np
import math
# Create random input and output data
#随机创造输入和输出数据
x = np.linspace(-math.pi, math.pi, 2000)
y = np.sin(x)
# Randomly initialize weights
#随机初始化权重
a = np.random.randn()
b = np.random.randn()
c = np.random.randn()
d = np.random.randn()
learning_rate = 1e-6
for t in range(2000):
# Forward pass: compute predicted y
# y = a + b x + c x^2 + d x^3
y_pred = a + b * x + c * x ** 2 + d * x ** 3
# Compute and print loss
loss = np.square(y_pred - y).sum()
if t % 100 == 99:
print(t, loss)
# Backprop to compute gradients of a, b, c, d with respect to loss
grad_y_pred = 2.0 * (y_pred - y)
grad_a = grad_y_pred.sum()
grad_b = (grad_y_pred * x).sum()
grad_c = (grad_y_pred * x ** 2).sum()
grad_d = (grad_y_pred * x ** 3).sum()
# Update weights
a -= learning_rate * grad_a
b -= learning_rate * grad_b
c -= learning_rate * grad_c
d -= learning_rate * grad_d
print(f'Result: y = {a} + {b} x + {c} x^2 + {d} x^3')输出结果：
Result: y = -0.020286201138995465 + 0.8361334547946534 x + 0.003499707260320742 x^2 + -0.09039916750860842 x^3
1.2 PyTorch:Tensors
Numpy is a great framework, but it cannot utilize GPUs to accelerate its numerical computations. For modern deep neural networks, GPUs often provide speedups of 50x or greater, so unfortunately numpy won’t be enough for modern deep learning.
【Numpy是一个很棒的框架，但是它不能利用gpu来加速它的数值计算。对于现代的深度神经网络，gpu通常提供50倍或更高的加速，因此不幸的是，numpy对于现代的深度学习还不够。】
Here we introduce the most fundamental PyTorch concept: the Tensor. A PyTorch Tensor is conceptually identical to a numpy array: a Tensor is an n-dimensional array, and PyTorch provides many functions for operating on these Tensors. Behind the scenes, Tensors can keep track of a computational graph and gradients, but they’re also useful as a generic tool for scientific computing.
【这里我们介绍PyTorch最基本的概念：张量。一个PyTorch张量在概念上与numpy数组相同：一个张量是一个n维数组，PyTorch提供了许多函数来操作这些张量。在幕后，张量可以跟踪计算图和梯度，但它们作为科学计算的通用工具也很有用。】
Also unlike numpy, PyTorch Tensors can utilize GPUs to accelerate their numeric computations. To run a PyTorch Tensor on GPU, you simply need to specify the correct device.
【与numpy不同的是，PyTorch tensor可以利用gpu来加速数值计算。要在GPU上运行一个PyTorch张量，你只需要指定正确的设备。】
Here we use PyTorch Tensors to fit a third order polynomial to sine function. Like the numpy example above we need to manually implement the forward and backward passes through the network:
【这里我们使用PyTorch张量来拟合一个三阶多项式到正弦函数。像上面的numpy例子一样，我们需要手动实现正向和向后通过网络:】
# -*- coding: utf-8 -*-
import torch
import math
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU
# Create random input and output data
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)
# Randomly initialize weights
a = torch.randn((), device=device, dtype=dtype)
b = torch.randn((), device=device, dtype=dtype)
c = torch.randn((), device=device, dtype=dtype)
d = torch.randn((), device=device, dtype=dtype)
learning_rate = 1e-6
for t in range(2000):
# Forward pass: compute predicted y
y_pred = a + b * x + c * x ** 2 + d * x ** 3
# Compute and print loss
loss = (y_pred - y).pow(2).sum().item()
if t % 100 == 99:
print(t, loss)
# Backprop to compute gradients of a, b, c, d with respect to loss
grad_y_pred = 2.0 * (y_pred - y)
grad_a = grad_y_pred.sum()
grad_b = (grad_y_pred * x).sum()
grad_c = (grad_y_pred * x ** 2).sum()
grad_d = (grad_y_pred * x ** 3).sum()
# Update weights using gradient descent
a -= learning_rate * grad_a
b -= learning_rate * grad_b
c -= learning_rate * grad_c
d -= learning_rate * grad_d
print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')输出结果：
Result: y = -0.05406272038817406 + 0.8315426707267761 x + 0.00932671781629324 x^2 + -0.08974616974592209 x^3
2 Autograd
2.1 PyTorch: Tensors and autograd
In the above examples, we had to manually implement both the forward and backward passes of our neural network. Manually implementing the backward pass is not a big deal for a small two-layer network, but can quickly get very hairy for large complex networks.
【在上面的例子中，我们必须手动实现神经网络的向前和向后传递。对于小型的两层网络来说，手动实现向后传递不是什么大问题，但对于大型的复杂网络来说，可能会变得非常棘手。】
Thankfully, we can use automatic differentiation to automate the computation of backward passes in neural networks. The autograd package in PyTorch provides exactly this functionality. When using autograd, the forward pass of your network will define a computational graph; nodes in the graph will be Tensors, and edges will be functions that produce output Tensors from input Tensors. Backpropagating through this graph then allows you to easily compute gradients.
【值得庆幸的是，我们可以使用自动微分来自动计算神经网络中的反向通道。PyTorch中的autograd包正好提供了这种功能。使用autograd时，你的网络的前向传递将定义一个计算图形；图中的节点将是张量，而边将是从输入张量产生输出张量的函数。然后通过这个图进行反向传播，可以方便地计算梯度。】
This sounds complicated, it’s pretty simple to use in practice. Each Tensor represents a node in a computational graph. If x is a Tensor that has x.requires_grad=True then x.grad is another Tensor holding the gradient of x with respect to some scalar value.
【这听起来很复杂，但在实践中却很简单。每个张量代表计算图中的一个节点。如果x是一个具有x.requires_grad=True的张量，那么x.grad就是另一个张量，它保持x相对于某个标量值的梯度。】
Here we use PyTorch Tensors and autograd to implement our fitting sine wave with third order polynomial example; now we no longer need to manually implement the backward pass through the network:
【这里我们使用PyTorch张量和自校正来实现我们的拟合正弦波与三阶多项式的例子；现在我们不再需要手动实现通过网络的向后传递:】
代码如下：
# -*- coding: utf-8 -*-
import torch
import math
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU
# Create Tensors to hold input and outputs.
# By default, requires_grad=False, which indicates that we do not need to
# compute gradients with respect to these Tensors during the backward pass.
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)
# Create random Tensors for weights. For a third order polynomial, we need
# 4 weights: y = a + b x + c x^2 + d x^3
# Setting requires_grad=True indicates that we want to compute gradients with
# respect to these Tensors during the backward pass.
a = torch.randn((), device=device, dtype=dtype, requires_grad=True)
b = torch.randn((), device=device, dtype=dtype, requires_grad=True)
c = torch.randn((), device=device, dtype=dtype, requires_grad=True)
d = torch.randn((), device=device, dtype=dtype, requires_grad=True)
learning_rate = 1e-6
for t in range(2000):
# Forward pass: compute predicted y using operations on Tensors.
y_pred = a + b * x + c * x ** 2 + d * x ** 3
# Compute and print loss using operations on Tensors.
# Now loss is a Tensor of shape (1,)
# loss.item() gets the scalar value held in the loss.
loss = (y_pred - y).pow(2).sum()
if t % 100 == 99:
print(t, loss.item())
# Use autograd to compute the backward pass. This call will compute the
# gradient of loss with respect to all Tensors with requires_grad=True.
# After this call a.grad, b.grad. c.grad and d.grad will be Tensors holding
# the gradient of the loss with respect to a, b, c, d respectively.
loss.backward()
# Manually update weights using gradient descent. Wrap in torch.no_grad()
# because weights have requires_grad=True, but we don't need to track this
# in autograd.
with torch.no_grad():
a -= learning_rate * a.grad
b -= learning_rate * b.grad
c -= learning_rate * c.grad
d -= learning_rate * d.grad
# Manually zero the gradients after updating weights
a.grad = None
b.grad = None
c.grad = None
d.grad = None
print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')输出结果：
Result: y = -0.03575234115123749 + 0.8381904363632202 x + 0.006167873740196228 x^2 + -0.09069175273180008 x^3
2.2 PyTorch: Defining new autograd functions
Under the hood, each primitive autograd operator is really two functions that operate on Tensors. The forward function computes output Tensors from input Tensors. The backward function receives the gradient of the output Tensors with respect to some scalar value, and computes the gradient of the input Tensors with respect to that same scalar value.
【在内部，每个原始autograd算子实际上是两个作用于张量的函数。正向函数从输入张量计算输出张量。反向函数接收输出张量相对于某个标量值的梯度，并计算输入张量相对于相同标量值的梯度。】
In PyTorch we can easily define our own autograd operator by defining a subclass of torch.autograd.Function and implementing the forward and backward functions. We can then use our new autograd operator by constructing an instance and calling it like a function, passing Tensors containing input data.
【在PyTorch中，我们可以通过定义torch.autograd.Function的子类并实现向前和向后的函数来轻松定义自己的autograd操作符。然后，我们可以通过构造一个实例，并像调用函数一样调用它，传递包含输入数据的张量(tensor)来使用新的自适应操作符。】
In this example we define our model as y=a+b P_3(c+dx)instead of y=a+bx+cx^2+dx^3 , where P_3(x)=0.5(5x^3-3x) is the Legendre polynomial of degree three. We write our own custom autograd function for computing forward and backward of P_3, and use it to implement our model:
【在这个例子中，我们定义我们的模型为y=a+b P_3(c+dx)而不是y=a+bx+cx^2+dx^3，其中P_3(x)=0.5(5x^3-3x)是三次的Legendre多项式。我们编写了自己的自定义autograd函数来计算P_3的正反向，并使用它来实现我们的模型:】
# -*- coding: utf-8 -*-
import torch
import math
class LegendrePolynomial3(torch.autograd.Function):
"""
We can implement our own custom autograd Functions by subclassing
torch.autograd.Function and implementing the forward and backward passes
which operate on Tensors.
"""
@staticmethod
def forward(ctx, input):
"""
In the forward pass we receive a Tensor containing the input and return
a Tensor containing the output. ctx is a context object that can be used
to stash information for backward computation. You can cache arbitrary
objects for use in the backward pass using the ctx.save_for_backward method.
在向前传递中，我们接收到一个包含输入的张量，并返回一个包含输出的张量。
ctx是一个上下文对象，可用于存储用于向后计算的信息。
您可以缓存任意对象，以便使用ctx进行向后传递时使用。save_for_backward方法。
"""
ctx.save_for_backward(input)
return 0.5 * (5 * input ** 3 - 3 * input)
@staticmethod
def backward(ctx, grad_output):
"""
In the backward pass we receive a Tensor containing the gradient of the loss
with respect to the output, and we need to compute the gradient of the loss
with respect to the input.
在反向传递中，我们收到一个张量包含了损失相对于输出的梯度，我们需要计算损失相对于输入的梯度。
"""
input, = ctx.saved_tensors
return grad_output * 1.5 * (5 * input ** 2 - 1)
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU
# Create Tensors to hold input and outputs.
# By default, requires_grad=False, which indicates that we do not need to
# compute gradients with respect to these Tensors during the backward pass.
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)
# Create random Tensors for weights. For this example, we need
# 4 weights: y = a + b * P3(c + d * x), these weights need to be initialized
# not too far from the correct result to ensure convergence.
# Setting requires_grad=True indicates that we want to compute gradients with
# respect to these Tensors during the backward pass.
a = torch.full((), 0.0, device=device, dtype=dtype, requires_grad=True)
b = torch.full((), -1.0, device=device, dtype=dtype, requires_grad=True)
c = torch.full((), 0.0, device=device, dtype=dtype, requires_grad=True)
d = torch.full((), 0.3, device=device, dtype=dtype, requires_grad=True)
learning_rate = 5e-6
for t in range(2000):
# To apply our Function, we use Function.apply method. We alias this as 'P3'.
P3 = LegendrePolynomial3.apply
# Forward pass: compute predicted y using operations; we compute
# P3 using our custom autograd operation.
y_pred = a + b * P3(c + d * x)
# Compute and print loss
loss = (y_pred - y).pow(2).sum()
if t % 100 == 99:
print(t, loss.item())
# Use autograd to compute the backward pass.
loss.backward()
# Update weights using gradient descent
with torch.no_grad():
a -= learning_rate * a.grad
b -= learning_rate * b.grad
c -= learning_rate * c.grad
d -= learning_rate * d.grad
# Manually zero the gradients after updating weights
a.grad = None
b.grad = None
c.grad = None
d.grad = None
print(f'Result: y = {a.item()} + {b.item()} * P3({c.item()} + {d.item()} x)')输出结果：
Result: y = -5.507681866134817e-09 + -2.208526849746704 * P3(1.4136716242063585e-09 + 0.2554861009120941 x)
3 nn module
3.1 PyTorch: nn
Computational graphs and autograd are a very powerful paradigm for defining complex operators and automatically taking derivatives; however for large neural networks raw autograd can be a bit too low-level.
【计算图和autograd是定义复杂算子和自动求导的一个非常强大的范例；然而，对于大型神经网络来说，原始的autograd可能有点低级。】
When building neural networks we frequently think of arranging the computation into layers, some of which have learnable parameters which will be optimized during learning.
【在构建神经网络时，我们经常考虑将计算分层，其中一些具有可学习的参数，这些参数将在学习过程中得到优化。】
In TensorFlow, packages like Keras, TensorFlow-Slim, and TFLearn provide higher-level abstractions over raw computational graphs that are useful for building neural networks.
【在TensorFlow中，像Keras、TensorFlow- Slim和TFLearn这样的包在原始计算图上提供了更高级的抽象，这对构建神经网络很有用。】
In PyTorch, the nn package serves this same purpose. The nn package defines a set of Modules, which are roughly equivalent to neural network layers. A Module receives input Tensors and computes output Tensors, but may also hold internal state such as Tensors containing learnable parameters. The nn package also defines a set of useful loss functions that are commonly used when training neural networks.
【在PyTorch中，nn包可以达到同样的目的。神经网络包定义了一组模块，它们大致相当于神经网络层。模块接收输入张量并计算输出张量，但也可以保存内部状态，比如包含可学习参数的张量。该神经网络包还定义了一组有用的损失函数，通常用于训练神经网络。】
In this example we use the nn package to implement our polynomial model network:
【在这个例子中，我们使用nn包来实现我们的多项式模型网络:】
# -*- coding: utf-8 -*-
import torch
import math
# Create Tensors to hold input and outputs.
x = torch.linspace(-math.pi, math.pi, 2000)
y = torch.sin(x)
# For this example, the output y is a linear function of (x, x^2, x^3), so
# we can consider it as a linear layer neural network. Let's prepare the
# tensor (x, x^2, x^3).
p = torch.tensor([1, 2, 3])
xx = x.unsqueeze(-1).pow(p) #a tensor of shape(2000,3)
# In the above code, x.unsqueeze(-1) has shape (2000, 1), and p has shape
# (3,), for this case, broadcasting semantics will apply to obtain a tensor
# of shape (2000, 3)
# Use the nn package to define our model as a sequence of layers. nn.Sequential
# is a Module which contains other Modules, and applies them in sequence to
# produce its output. The Linear Module computes output from input using a
# linear function, and holds internal Tensors for its weight and bias.
# The Flatten layer flatens the output of the linear layer to a 1D tensor,
# to match the shape of `y`.
"""
使用nn包将我们的模型定义为一个层序列。
nn.Sequential是一个包含其他模块的模块，并按顺序应用它们来产生它的输出。
Linear Module使用一个线性函数从输入计算输出，并保留其权值和偏置的内部张量。
Flatten层将线性层的输出展成一维张量，以匹配' y '的形状。
"""
model = torch.nn.Sequential(
torch.nn.Linear(3, 1),
torch.nn.Flatten(0, 1)
)
# The nn package also contains definitions of popular loss functions; in this
# case we will use Mean Squared Error (MSE) as our loss function.
loss_fn = torch.nn.MSELoss(reduction='sum')
learning_rate = 1e-6
for t in range(2000):
# Forward pass: compute predicted y by passing x to the model. Module objects
# override the __call__ operator so you can call them like functions. When
# doing so you pass a Tensor of input data to the Module and it produces
# a Tensor of output data.
"""
正向传递:通过将x传递给模型来计算预测的y。模块对象覆盖了__call__操作符，所以你可以像调用函数一样调用它们。
当你这样做的时候，你把一个输入数据的张量传递给模块，它就会产生一个输出数据的张量。
"""
y_pred = model(xx)
# Compute and print loss. We pass Tensors containing the predicted and true
# values of y, and the loss function returns a Tensor containing the
# loss.
loss = loss_fn(y_pred, y)
if t % 100 == 99:
print(t, loss.item())
# Zero the gradients before running the backward pass.
model.zero_grad()
# Backward pass: compute gradient of the loss with respect to all the learnable
# parameters of the model. Internally, the parameters of each Module are stored
# in Tensors with requires_grad=True, so this call will compute gradients for
# all learnable parameters in the model.
loss.backward()
# Update the weights using gradient descent. Each parameter is a Tensor, so
# we can access its gradients like we did before.
with torch.no_grad():
for param in model.parameters():
param -= learning_rate * param.grad
# You can access the first layer of `model` like accessing the first item of a list
linear_layer = model[0]
# For linear layer, its parameters are stored as `weight` and `bias`.
print(f'Result: y = {linear_layer.bias.item()} + {linear_layer.weight[:, 0].item()} x + {linear_layer.weight[:, 1].item()} x^2 + {linear_layer.weight[:, 2].item()} x^3')结果如下：
表达式：
Result: y = -0.011929822154343128 + 0.8352645039558411 x + 0.0020580925047397614 x^2 + -0.09027556329965591 x^3
3.2 PyTorch: optim
Up to this point we have updated the weights of our models by manually mutating the Tensors holding learnable parameters with torch.no_grad(). This is not a huge burden for simple optimization algorithms like stochastic gradient descent, but in practice we often train neural networks using more sophisticated optimizers like AdaGrad, RMSProp, Adam, etc.
【到目前为止，我们已经通过使用torch.no_grad()手动改变持有可学习参数的张量来更新模型的权值。对于随机梯度下降等简单的优化算法来说，这不是一个巨大的负担，但在实践中，我们经常使用更复杂的优化器来训练神经网络，如AdaGrad、RMSProp、Adam等。】
The optim package in PyTorch abstracts the idea of an optimization algorithm and provides implementations of commonly used optimization algorithms.
【PyTorch中的optim包抽象了优化算法的思想，并提供了常用的优化算法的实现。】
In this example we will use the nn package to define our model as before, but we will optimize the model using the RMSprop algorithm provided by the optim package:
【在本例中，我们将像之前一样使用nn包来定义我们的模型，但我们将使用optim包提供的RMSprop算法来优化模型:】
# -*- coding: utf-8 -*-
import torch
import math
# Create Tensors to hold input and outputs.
x = torch.linspace(-math.pi, math.pi, 2000)
y = torch.sin(x)
# Prepare the input tensor (x, x^2, x^3).
p = torch.tensor([1, 2, 3])
xx = x.unsqueeze(-1).pow(p)
# Use the nn package to define our model and loss function.
model = torch.nn.Sequential(
torch.nn.Linear(3, 1),
torch.nn.Flatten(0, 1)
)
loss_fn = torch.nn.MSELoss(reduction='sum')
# Use the optim package to define an Optimizer that will update the weights of
# the model for us. Here we will use RMSprop; the optim package contains many other
# optimization algorithms. The first argument to the RMSprop constructor tells the
# optimizer which Tensors it should update.
learning_rate = 1e-3
optimizer = torch.optim.RMSprop(model.parameters(), lr=learning_rate)
for t in range(2000):
# Forward pass: compute predicted y by passing x to the model.
y_pred = model(xx)
# Compute and print loss.
loss = loss_fn(y_pred, y)
if t % 100 == 99:
print(t, loss.item())
# Before the backward pass, use the optimizer object to zero all of the
# gradients for the variables it will update (which are the learnable
# weights of the model). This is because by default, gradients are
# accumulated in buffers( i.e, not overwritten) whenever .backward()
# is called. Checkout docs of torch.autograd.backward for more details.
optimizer.zero_grad()
# Backward pass: compute gradient of the loss with respect to model
# parameters
loss.backward()
# Calling the step function on an Optimizer makes an update to its
# parameters
optimizer.step()
linear_layer = model[0]
print(f'Result: y = {linear_layer.bias.item()} + {linear_layer.weight[:, 0].item()} x + {linear_layer.weight[:, 1].item()} x^2 + {linear_layer.weight[:, 2].item()} x^3')结果如下：
Result: y = -4.840137989958748e-06 + 0.8572000861167908 x + -4.832752892980352e-06 x^2 + -0.0928042009472847 x^3
3.3 PyTorch: Custom nn Modules
Sometimes you will want to specify models that are more complex than a sequence of existing Modules; for these cases you can define your own Modules by subclassing nn.Module and defining a forward which receives input Tensors and produces output Tensors using other modules or other autograd operations on Tensors.
【有时你会想要指定比一系列现有模块更复杂的模型；对于这些情况，你可以通过子类化nn.Module来定义你自己的模块，并定义一个forward，该forward接收输入张量，并使用其他模块或其他对张量的自适应操作生成输出张量。】
In this example we implement our third order polynomial as a custom Module subclass:
【在这个例子中，我们将三阶多项式实现为一个自定义的模块子类:】
# -*- coding: utf-8 -*-
import torch
import math
class Polynomial3(torch.nn.Module):
def __init__(self):
"""
In the constructor we instantiate four parameters and assign them as
member parameters.
"""
super().__init__()
self.a = torch.nn.Parameter(torch.randn(()))
self.b = torch.nn.Parameter(torch.randn(()))
self.c = torch.nn.Parameter(torch.randn(()))
self.d = torch.nn.Parameter(torch.randn(()))
def forward(self, x):
"""
In the forward function we accept a Tensor of input data and we must return
a Tensor of output data. We can use Modules defined in the constructor as
well as arbitrary operators on Tensors.
"""
return self.a + self.b * x + self.c * x ** 2 + self.d * x ** 3
def string(self):
"""
Just like any class in Python, you can also define custom method on PyTorch modules
"""
return f'y = {self.a.item()} + {self.b.item()} x + {self.c.item()} x^2 + {self.d.item()} x^3'
# Create Tensors to hold input and outputs.
x = torch.linspace(-math.pi, math.pi, 2000)
y = torch.sin(x)
# Construct our model by instantiating the class defined above
model = Polynomial3()
# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters (defined
# with torch.nn.Parameter) which are members of the model.
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-6)
for t in range(2000):
# Forward pass: Compute predicted y by passing x to the model
y_pred = model(x)
# Compute and print loss
loss = criterion(y_pred, y)
if t % 100 == 99:
print(t, loss.item())
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(f'Result: {model.string()}')输出结果：
Result: y = -0.012196008116006851 + 0.8496573567390442 x + 0.0021040153224021196 x^2 + -0.09232281893491745 x^3
3.4 PyTorch: Control Flow + Weight Sharing
As an example of dynamic graphs and weight sharing, we implement a very strange model: a third-fifth order polynomial that on each forward pass chooses a random number between 3 and 5 and uses that many orders, reusing the same weights multiple times to compute the fourth and fifth order.
【作为动态图和权值共享的一个例子，我们实现了一个非常奇怪的模型：一个三至五阶多项式，在每次前向传递中选择一个3到5之间的随机数，并使用该阶数，多次重用相同的权值来计算四阶和五阶。】
For this model we can use normal Python flow control to implement the loop, and we can implement weight sharing by simply reusing the same parameter multiple times when defining the forward pass.
【对于这个模型，我们可以使用普通的Python流控制来实现循环，并且在定义forward传递时，我们可以通过简单地多次重用相同的参数来实现权重共享。】
We can easily implement this model as a Module subclass:
【我们可以很容易地将这个模型实现为一个Module的子类:】
# -*- coding: utf-8 -*-
import random
import torch
import math
class DynamicNet(torch.nn.Module):
def __init__(self):
"""
In the constructor we instantiate five parameters and assign them as members.
"""
super().__init__()
self.a = torch.nn.Parameter(torch.randn(()))
self.b = torch.nn.Parameter(torch.randn(()))
self.c = torch.nn.Parameter(torch.randn(()))
self.d = torch.nn.Parameter(torch.randn(()))
self.e = torch.nn.Parameter(torch.randn(()))
def forward(self, x):
"""
For the forward pass of the model, we randomly choose either 4, 5
and reuse the e parameter to compute the contribution of these orders.
Since each forward pass builds a dynamic computation graph, we can use normal
Python control-flow operators like loops or conditional statements when
defining the forward pass of the model.
Here we also see that it is perfectly safe to reuse the same parameter many
times when defining a computational graph.
"""
y = self.a + self.b * x + self.c * x ** 2 + self.d * x ** 3
for exp in range(4, random.randint(4, 6)):
y = y + self.e * x ** exp
return y
def string(self):
"""
Just like any class in Python, you can also define custom method on PyTorch modules
"""
return f'y = {self.a.item()} + {self.b.item()} x + {self.c.item()} x^2 + {self.d.item()} x^3 + {self.e.item()} x^4 ? + {self.e.item()} x^5 ?'
# Create Tensors to hold input and outputs.
x = torch.linspace(-math.pi, math.pi, 2000)
y = torch.sin(x)
# Construct our model by instantiating the class defined above
model = DynamicNet()
# Construct our loss function and an Optimizer. Training this strange model with
# vanilla stochastic gradient descent is tough, so we use momentum
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-8, momentum=0.9)
for t in range(30000):
# Forward pass: Compute predicted y by passing x to the model
y_pred = model(x)
# Compute and print loss
loss = criterion(y_pred, y)
if t % 2000 == 1999:
print(t, loss.item())
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(f'Result: {model.string()}')结果如下：
Result: y = -0.004479429684579372 + 0.8554535508155823 x + 0.0002896672813221812 x^2 + -0.09336008131504059 x^3 + 7.368111255345866e-05 x^4 ? + 7.368111255345866e-05 x^5 ?
官方链接：Learning PyTorch with Examples — PyTorch Tutorials 1.10.1+cu102 documentation
Author: Justin Johnson
说明：记录学习笔记，如果错误欢迎指正！写文章不易，转载请联系我。
959
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
