学习PyTorch与实例

最新推荐文章于 2024-06-18 22:30:00 发布

lillllllll

最新推荐文章于 2024-06-18 22:30:00 发布

阅读量281

点赞数 1

分类专栏：深度技术学习文章标签： PyTorch

原文链接：https://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-defining-new-autograd-functions

版权

深度技术学习专栏收录该内容

12 篇文章 3 订阅

订阅专栏

本文翻译PyTorch官方文档 Learning PyTorch with Examples

本教程通过自包含的示例介绍PyTorch的基本概念。
作者: Justin Johnson
PyTorch的核心是两个主要特征：

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

我们将使用完全连接的ReLU网络作为运行示例。网络将具有单个隐藏层，并且将通过最小化网络输出与真实输出之间的欧几里德距离来训练梯度下降以适合随机数据。

Tensors

热身：numpy
在介绍PyTorch之前，我们将首先使用numpy实现网络。
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; 它对计算图，深度学习或渐变都一无所知。但是，通过使用numpy操作手动实现网络的前向和后向传递，我们可以轻松地使用numpy将两层网络适配到随机数据：

# -*- coding: utf-8 -*-
import numpy as np

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random input and output data
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)

# Randomly initialize weights
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y
    h = x.dot(w1)
    h_relu = np.maximum(h, 0)
    y_pred = h_relu.dot(w2)

    # Compute and print loss
    loss = np.square(y_pred - y).sum()
    print(t, loss)

    # Backprop to compute gradients of w1 and w2 with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_w2 = h_relu.T.dot(grad_y_pred)
    grad_h_relu = grad_y_pred.dot(w2.T)
    grad_h = grad_h_relu.copy()
    grad_h[h < 0] = 0
    grad_w1 = x.T.dot(grad_h)

    # Update weights
    w1 -= learning_rate * grad_w1
    w2 -= learning_rate * grad_w2

PyTorch: Tensors

Numpy是一个很棒的框架，但它不能利用GPU来加速其数值计算。对于现代深度神经网络，GPU通常提供50倍或更高的加速，因此不幸的是，numpy对于现代深度学习来说还不够。
在这里，我们介绍最基本的PyTorch概念：Tensor。 PyTorch Tensor在概念上与numpy数组相同：Tensor是一个n维数组，PyTorch提供了许多用于在这些Tensors上运算的函数。在幕后，Tensors可以跟踪计算图和渐变，但它们也可用作科学计算的通用工具。与numpy不同，PyTorch Tensors可以利用GPU加速其数值计算。要在GPU上运行PyTorch Tensor，只需将其转换为新的数据类型即可。在这里，我们使用PyTorch Tensors将双层网络与随机数据相匹配。就像上面的numpy示例一样，我们需要手动实现网络中的前向和后向传递：

# -*- coding: utf-8 -*-

import torch


dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random input and output data
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)

# Randomly initialize weights
w1 = torch.randn(D_in, H, device=device, dtype=dtype)
w2 = torch.randn(H, D_out, device=device, dtype=dtype)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y
    h = x.mm(w1)
    h_relu = h.clamp(min=0)
    y_pred = h_relu.mm(w2)

    # Compute and print loss
    loss = (y_pred - y).pow(2).sum().item()
    if t % 100 == 99:
        print(t, loss)

    # Backprop to compute gradients of w1 and w2 with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_w2 = h_relu.t().mm(grad_y_pred)
    grad_h_relu = grad_y_pred.mm(w2.t())
    grad_h = grad_h_relu.clone()
    grad_h[h < 0] = 0
    grad_w1 = x.t().mm(grad_h)

    # Update weights using gradient descent
    w1 -= learning_rate * grad_w1
    w2 -= learning_rate * grad_w2

Autograd

PyTorch：Tensors和autograd

    在上面的例子中，我们不得不手动实现神经网络的前向和后向传递。手动实现反向传递对于小型双层网络来说并不是什么大问题，但对于大型复杂网络来说很快就会变得非常繁琐。
    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后向传递。 PyTorch中的autograd包提供了这个功能。使用autograd时，网络的正向传递将定义计算图形;图中的节点是张量，图中的边是从输入张量产生输出张量的函数。通过此图反向传播，您可以轻松计算渐变。
    这听起来很复杂，在实践中使用起来非常简单。每个Tensor表示计算图中的节点。如果x是具有x.requires_grad = True的Tensor，则x.grad是关于某个标量的梯度值，它也是一个Tensor。
在这里，我们使用PyTorch Tensors和autograd来实现我们的双层网络;现在我们不再需要手动实现通过网络的反向传递：

# -*- coding: utf-8 -*-
import torch

dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold input and outputs.
# Setting requires_grad=False indicates that we do not need to compute gradients
# with respect to these Tensors during the backward pass.
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)

# Create random Tensors for weights.
# Setting requires_grad=True indicates that we want to compute gradients with
# respect to these Tensors during the backward pass.
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y using operations on Tensors; these
    # are exactly the same operations we used to compute the forward pass using
    # Tensors, but we do not need to keep references to intermediate values since
    # we are not implementing the backward pass by hand.
    y_pred = x.mm(w1).clamp(min=0).mm(w2)

    # 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 w1.grad and w2.grad will be Tensors holding the gradient
    # of the loss with respect to w1 and w2 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.
    # An alternative way is to operate on weight.data and weight.grad.data.
    # Recall that tensor.data gives a tensor that shares the storage with
    # tensor, but doesn't track history.
    # You can also use torch.optim.SGD to achieve this.
    with torch.no_grad():
        w1 -= learning_rate * w1.grad
        w2 -= learning_rate * w2.grad

        # Manually zero the gradients after updating weights
        w1.grad.zero_()
        w2.grad.zero_()

PyTorch: 定义新的 autograd 函数

在引擎盖下，每个原始autograd运算符实际上是两个在Tensors上运行的函数。 forward函数从输入Tensors计算输出张量。向后函数接收输出张量相对于某个标量值的梯度，并根据相同的标量值计算输入张量的梯度。

在PyTorch中，我们可以通过定义torch.autograd.Function的子类并实现前向和后向函数来轻松定义我们自己的autograd运算符。然后，我们可以通过构造一个实例并将其称为函数来使用我们的新autograd运算符，并传递包含输入数据的Tensors。

在这个例子中，我们定义了自己的自定义autograd函数来执行ReLU非线性，并使用它来实现我们的双层网络：

# -*- coding: utf-8 -*-
import torch


class MyReLU(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.
        """
        ctx.save_for_backward(input)
        return input.clamp(min=0)

    @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.
        """
        input, = ctx.saved_tensors
        grad_input = grad_output.clone()
        grad_input[input < 0] = 0
        return grad_input


dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold input and outputs.
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)

# Create random Tensors for weights.
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)

learning_rate = 1e-6
for t in range(500):
    # To apply our Function, we use Function.apply method. We alias this as 'relu'.
    relu = MyReLU.apply

    # Forward pass: compute predicted y using operations; we compute
    # ReLU using our custom autograd operation.
    y_pred = relu(x.mm(w1)).mm(w2)

    # 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():
        w1 -= learning_rate * w1.grad
        w2 -= learning_rate * w2.grad

        # Manually zero the gradients after updating weights
        w1.grad.zero_()
        w2.grad.zero_()

TensorFlow: Static Graphs

PyTorch autograd看起来很像TensorFlow：在两个框架中我们定义了一个计算图，并使用自动微分来计算梯度。两者之间最大的区别是TensorFlow的计算图是静态的，PyTorch使用动态计算图。
在TensorFlow中，我们定义计算图一次，然后一遍又一遍地执行相同的图，可能将不同的输入数据提供给图。在PyTorch中，每个前向传递定义了一个新的计算图。
静态图很好，因为你可以预先优化图形;例如，框架可能决定融合某些图形操作以提高效率，或者提出一种策略，用于在多个GPU或许多机器上分布图形。如果您反复使用相同的图表，那么这个可能代价高昂的前期优化可以摊销，因为相同的图表会反复重新运行。
静态和动态图表不同的一个方面是控制流程。对于某些模型，我们可能希望对每个数据点执行不同的计算;例如，对于每个数据点，可以针对不同数量的时间步长展开循环网络;这种展开可以作为循环实现。使用静态图形，循环结构需要是图形的一部分;因此，TensorFlow提供了诸如tf.scan之类的运算符，用于将循环嵌入到图中。使用动态图形情况更简单：因为我们为每个示例动态构建图形，我们可以使用常规命令流程控制来执行每个输入不同的计算。
与上面的PyTorch autograd示例相比，这里我们使用TensorFlow来拟合一个简单的双层网：

nn module

PyTorch: nn

计算图和autograd是定义复杂运算符和自动获取导数的非常强大的范例;然而，对于大型神经网络，原始autograd可能有点太低级别。
在构建神经网络时，我们经常考虑将计算安排到层中，其中一些层具有可学习的参数，这些参数将在学习期间进行优化。
在TensorFlow中，Keras，TensorFlow-Slim和TFLearn等软件包提供了对构建神经网络有用的原始计算图形的更高级别的抽象。
在PyTorch中，nn包服务于同样的目的。 nn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，但也可以保持内部状态，例如包含可学习参数的张量。 nn包还定义了一组在训练神经网络时常用的有用损失函数。
在这个例子中，我们使用nn包来实现我们的双层网络：

# -*- coding: utf-8 -*-
import torch

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# 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. Each Linear Module computes output from input using a
# linear function, and holds internal Tensors for its weight and bias.
model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
)

# 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-4
for t in range(500):
    # 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.
    y_pred = model(x)

    # 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

PyTorch: optim

到目前为止，我们通过手动改变持有可学习参数的Tensors来更新模型的权重（使用torch.no_grad（）或.data以避免在autograd中跟踪历史记录）。对于像随机梯度下降这样的简单优化算法来说，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如AdaGrad，RMSProp，Adam等来训练神经网络。
PyTorch中的optim包提取了优化算法的思想，并提供了常用优化算法的实现。
在这个例子中，我们将使用nn包像以前一样定义我们的模型，但我们将使用optim包提供的Adam算法优化模型：

# -*- coding: utf-8 -*-
import torch

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# Use the nn package to define our model and loss function.
model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
)
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 Adam; the optim package contains many other
# optimization algoriths. The first argument to the Adam constructor tells the
# optimizer which Tensors it should update.
learning_rate = 1e-4
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for t in range(500):
    # Forward pass: compute predicted y by passing x to the model.
    y_pred = model(x)

    # 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()

PyTorch：自定义nn模块

有时您需要指定比现有模块序列更复杂的模型; 对于这些情况，您可以通过继承nn.Module并定义一个接收输入Tensors并使用其他模块或Tensors上的其他autograd操作生成输出Tensors的forward来定义您自己的模块。
在这个例子中，我们将我们的双层网络实现为自定义模块子类：

# -*- coding: utf-8 -*-
import torch


class TwoLayerNet(torch.nn.Module):
    def __init__(self, D_in, H, D_out):
        """
        In the constructor we instantiate two nn.Linear modules and assign them as
        member variables.
        """
        super(TwoLayerNet, self).__init__()
        self.linear1 = torch.nn.Linear(D_in, H)
        self.linear2 = torch.nn.Linear(H, D_out)

    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.
        """
        h_relu = self.linear1(x).clamp(min=0)
        y_pred = self.linear2(h_relu)
        return y_pred


# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# Construct our model by instantiating the class defined above
model = TwoLayerNet(D_in, H, D_out)

# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters of the two
# nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
for t in range(500):
    # 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()

PyTorch：控制流+重量共享

作为动态图和权重共享的一个例子，我们实现了一个非常奇怪的模型：一个完全连接的ReLU网络，在每个正向传递上选择1到4之间的随机数并使用那么多隐藏层，重复使用相同的权重多次计算最里面的隐藏层。
对于这个模型，我们可以使用普通的Python流控制来实现循环，并且我们可以通过在定义正向传递时多次重复使用相同的模块来实现最内层之间的权重共享。我们可以轻松地将此模型实现为Module子类：

# -*- coding: utf-8 -*-
import random
import torch


class DynamicNet(torch.nn.Module):
    def __init__(self, D_in, H, D_out):
        """
        In the constructor we construct three nn.Linear instances that we will use
        in the forward pass.
        """
        super(DynamicNet, self).__init__()
        self.input_linear = torch.nn.Linear(D_in, H)
        self.middle_linear = torch.nn.Linear(H, H)
        self.output_linear = torch.nn.Linear(H, D_out)

    def forward(self, x):
        """
        For the forward pass of the model, we randomly choose either 0, 1, 2, or 3
        and reuse the middle_linear Module that many times to compute hidden layer
        representations.

        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 Module many
        times when defining a computational graph. This is a big improvement from Lua
        Torch, where each Module could be used only once.
        """
        h_relu = self.input_linear(x).clamp(min=0)
        for _ in range(random.randint(0, 3)):
            h_relu = self.middle_linear(h_relu).clamp(min=0)
        y_pred = self.output_linear(h_relu)
        return y_pred


# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# Construct our model by instantiating the class defined above
model = DynamicNet(D_in, H, D_out)

# 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-4, momentum=0.9)
for t in range(500):
    # 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()