Pytorch使用autograd.Function自定义拓展神经网络

我们知道CNN这类人工神经网络都基于BP算法进行优化，因此需要误差关于权重是连续可导的，这是可以运用BP算法的前提条件；也有一些网络不满足这个条件。

1.可导

对于可连续求导的神经网络构建时采用nn.Module类即可，此时仅仅需要改写__init__和forward方法，torch会自动求导，如下面的例子：

import torch
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 3x3 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 3)
        self.conv2 = nn.Conv2d(6, 16, 3)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 6 * 6, 120)  # 6*6 from image dimension
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)

2.不可导

当构建的神经网络不满足连续可导时，通常是某一部分函数不可导，这时需要采用autograd.Function对不可导的部分自己定义backward方法。以下面这个例子说明autograd.Function的用法：

y = x*w +b      # 自己定义的LinearFunction
z = f(y)

其中，grad_output = dz/dy
根据复合函数求导法则:
1. dz/dx =  dz/dy * dy/dx = grad_output*dy/dx = grad_output*w
2. dz/dw =  dz/dy * dy/dw = grad_output*dy/dw = grad_output*x
3. dz/db = dz/dy * dy/db = grad_output*1

import torch.autograd.Function as Function
class LinearFunction(Function):
　  # 创建torch.autograd.Function类的一个子类
    # 必须是staticmethod
    @staticmethod
    # 第一个是ctx，第二个是input，其他是可选参数。
    # ctx在这里类似self，ctx的属性可以在backward中调用。
    # 自己定义的Function中的forward()方法，所有的Variable参数将会转成tensor！因此这里的input也是tensor．在传入forward前，autograd engine会自动将Variable unpack成Tensor。
    def forward(ctx, input, weight, bias=None):
        print(type(input))
        ctx.save_for_backward(input, weight, bias) # 将Tensor转变为Variable保存到ctx中
        output = input.mm(weight.t())  # torch.t()方法，对2D tensor进行转置
        if bias is not None:
            output += bias.unsqueeze(0).expand_as(output)　＃unsqueeze(0) 扩展处第0维
            # expand_as(tensor)等价于expand(tensor.size()), 将原tensor按照新的size进行扩展
        return output

    @staticmethod
    def backward(ctx, grad_output): 
        # grad_output为反向传播上一级计算得到的梯度值
        input, weight, bias = ctx.saved_variables
        grad_input = grad_weight = grad_bias = None
        # 分别代表输入,权值,偏置三者的梯度
        # 判断三者对应的Variable是否需要进行反向求导计算梯度
        if ctx.needs_input_grad[0]:
            grad_input = grad_output.mm(weight) # 复合函数求导，链式法则
        if ctx.needs_input_grad[1]:
            grad_weight = grad_output.t().mm(input)　# 复合函数求导，链式法则
        if bias is not None and ctx.needs_input_grad[2]:
            grad_bias = grad_output.sum(0).squeeze(0)

        return grad_input, grad_weight, grad_bias

一般可以将其封装为一个方法来调用。

#建议把新操作封装在一个函数中
def linear(input, weight, bias=None):
    # First braces create a Function object. Any arguments given here
    # will be passed to __init__. Second braces will invoke the __call__
    # operator, that will then use forward() to compute the result and
    # return it.
    return LinearFunction()(input, weight, bias)#调用forward()

# 或者使用apply方法对自己定义的方法取个别名,再调用
linear = LinearFunction.apply
linear(input, weight, bias)

#检查实现的backward()是否正确
from torch.autograd import gradcheck
# gradchek takes a tuple of tensor as input, check if your gradient
# evaluated with these tensors are close enough to numerical
# approximations and returns True if they all verify this condition.
input = (Variable(torch.randn(20,20).double(), requires_grad=True),)
test = gradcheck(LinearFunction(), input, eps=1e-6, atol=1e-4)
print(test)  #　没问题的话输出True

下面则是将这个自定义求导的函数嵌入到自定义的神经网络中，网络架构用nn.Module实现：

import torch.nn as nn
class Linear(nn.Module):
    def __init__(self, input_features, output_features, bias=True):
        super(Linear, self).__init__()
        self.input_features = input_features
        self.output_features = output_features
        # nn.Parameter is a special kind of Variable, that will get
        # automatically registered as Module's parameter once it's assigned
        # 这个很重要！ Parameters是默认需要梯度的！
        self.weight = nn.Parameter(torch.Tensor(output_features, input_features))
        if bias:
            self.bias = nn.Parameter(torch.Tensor(output_features))
        else:
            # You should always register all possible parameters, but the
            # optional ones can be None if you want.
            self.register_parameter('bias', None)
        # Not a very smart way to initialize weights
        self.weight.data.uniform_(-0.1, 0.1)
        if bias is not None:
            self.bias.data.uniform_(-0.1, 0.1)
    def forward(self, input):
        # See the autograd section for explanation of what happens here.
        return LinearFunction.apply(input, self.weight, self.bias)
        # 或者　return LinearFunction()(input, self.weight, self.bias)

最后2行代码，是调用LinearFuction的两种方法，一个是用apply，另一个是创建实例。注意不能用LinearFunction().forward(input, self.weight, self.bias)，因为这样仅仅是调用LinearFunction的forward方法，torch对网络Linear的forwardz中的函数自动求导时，进入LinearFunction的forward方法并自动求导，而不会去调用LinearFunction中自定义的backward方法。

最后放上官方教程

# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable


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.FloatTensor
# dtype = torch.cuda.FloatTensor # 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, and wrap them in Variables.
x = Variable(torch.randn(N, D_in).type(dtype), requires_grad=False)
y = Variable(torch.randn(N, D_out).type(dtype), requires_grad=False)

# Create random Tensors for weights, and wrap them in Variables.
w1 = Variable(torch.randn(D_in, H).type(dtype), requires_grad=True)
w2 = Variable(torch.randn(H, D_out).type(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 on Variables; 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()
    print(t, loss.data[0])

    # Use autograd to compute the backward pass.
    loss.backward()

    # Update weights using gradient descent
    w1.data -= learning_rate * w1.grad.data
    w2.data -= learning_rate * w2.grad.data

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

参考博客：https://blog.csdn.net/Hungryof/article/details/78346304

https://blog.csdn.net/tsq292978891/article/details/79364140