欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

pytorch自定義不可導激活函數(shù)的操作

 更新時間：2021年06月05日 14:46:53   作者：Luna_Lovegood_001  
這篇文章主要介紹了pytorch自定義不可導激活函數(shù)的操作，具有很好的參考價值，希望大家有所幫助。如有錯誤或未考慮完全的地方，望不吝賜教

pytorch自定義不可導激活函數(shù)

今天自定義不可導函數(shù)的時候遇到了一個大坑。

首先我需要自定義一個函數(shù)：sign_f

import torch
from torch.autograd import Function
import torch.nn as nn
class sign_f(Function):
    @staticmethod
    def forward(ctx, inputs):
        output = inputs.new(inputs.size())
        output[inputs >= 0.] = 1
        output[inputs < 0.] = -1
        ctx.save_for_backward(inputs)
        return output

    @staticmethod
    def backward(ctx, grad_output):
        input_, = ctx.saved_tensors
        grad_output[input_>1.] = 0
        grad_output[input_<-1.] = 0
        return grad_output

然后我需要把它封裝為一個module 類型，就像 nn.Conv2d 模塊 封裝 f.conv2d 一樣，于是

import torch
from torch.autograd import Function
import torch.nn as nn
class sign_(nn.Module):
	# 我需要的module
    def __init__(self, *kargs, **kwargs):
        super(sign_, self).__init__(*kargs, **kwargs)
        
    def forward(self, inputs):
    	# 使用自定義函數(shù)
        outs = sign_f(inputs)
        return outs

class sign_f(Function):
    @staticmethod
    def forward(ctx, inputs):
        output = inputs.new(inputs.size())
        output[inputs >= 0.] = 1
        output[inputs < 0.] = -1
        ctx.save_for_backward(inputs)
        return output

    @staticmethod
    def backward(ctx, grad_output):
        input_, = ctx.saved_tensors
        grad_output[input_>1.] = 0
        grad_output[input_<-1.] = 0
        return grad_output

結(jié)果報錯

TypeError: backward() missing 2 required positional arguments: 'ctx' and 'grad_output'

我試了半天，發(fā)現(xiàn)自定義函數(shù)后面要加 apply ，詳細見下面

import torch
from torch.autograd import Function
import torch.nn as nn
class sign_(nn.Module):

    def __init__(self, *kargs, **kwargs):
        super(sign_, self).__init__(*kargs, **kwargs)
        self.r = sign_f.apply ### <-----注意此處
        
    def forward(self, inputs):
        outs = self.r(inputs)
        return outs

class sign_f(Function):
    @staticmethod
    def forward(ctx, inputs):
        output = inputs.new(inputs.size())
        output[inputs >= 0.] = 1
        output[inputs < 0.] = -1
        ctx.save_for_backward(inputs)
        return output

    @staticmethod
    def backward(ctx, grad_output):
        input_, = ctx.saved_tensors
        grad_output[input_>1.] = 0
        grad_output[input_<-1.] = 0
        return grad_output

問題解決了！

PyTorch自定義帶學習參數(shù)的激活函數(shù)（如sigmoid）

有的時候我們需要給損失函數(shù)設(shè)一個超參數(shù)但是又不想設(shè)固定閾值想和網(wǎng)絡(luò)一起自動學習，例如給Sigmoid一個參數(shù)alpha進行調(diào)節(jié)

在這里插入圖片描述

在這里插入圖片描述

函數(shù)如下：

import torch.nn as nn
import torch
class LearnableSigmoid(nn.Module):
    def __init__(self, ):
        super(LearnableSigmoid, self).__init__()
        self.weight = torch.nn.Parameter(torch.FloatTensor(1), requires_grad=True)

        self.reset_parameters()
    def reset_parameters(self):
        self.weight.data.fill_(1.0)
        
    def forward(self, input):
        return 1/(1 +  torch.exp(-self.weight*input))

驗證和Sigmoid的一致性

class LearnableSigmoid(nn.Module):
    def __init__(self, ):
        super(LearnableSigmoid, self).__init__()
        self.weight = torch.nn.Parameter(torch.FloatTensor(1), requires_grad=True)

        self.reset_parameters()
    def reset_parameters(self):
        self.weight.data.fill_(1.0)
        
    def forward(self, input):
        return 1/(1 +  torch.exp(-self.weight*input))
   
Sigmoid = nn.Sigmoid()
LearnSigmoid = LearnableSigmoid()
input = torch.tensor([[0.5289, 0.1338, 0.3513],
        [0.4379, 0.1828, 0.4629],
        [0.4302, 0.1358, 0.4180]])

print(Sigmoid(input))
print(LearnSigmoid(input))

輸出結(jié)果

tensor([[0.6292, 0.5334, 0.5869],
[0.6078, 0.5456, 0.6137],
[0.6059, 0.5339, 0.6030]])

tensor([[0.6292, 0.5334, 0.5869],
[0.6078, 0.5456, 0.6137],
[0.6059, 0.5339, 0.6030]], grad_fn=<MulBackward0>)

驗證權(quán)重是不是會更新

import torch.nn as nn
import torch
import torch.optim as optim
class LearnableSigmoid(nn.Module):
    def __init__(self, ):
        super(LearnableSigmoid, self).__init__()
        self.weight = torch.nn.Parameter(torch.FloatTensor(1), requires_grad=True)

        self.reset_parameters()

    def reset_parameters(self):
        self.weight.data.fill_(1.0)
        
    def forward(self, input):
        return 1/(1 +  torch.exp(-self.weight*input))
        
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()       
        self.LSigmoid = LearnableSigmoid()
    def forward(self, x):                
        x = self.LSigmoid(x)
        return x

net = Net()  
print(list(net.parameters()))
optimizer = optim.SGD(net.parameters(), lr=0.01)
learning_rate=0.001
input_data=torch.randn(10,2)
target=torch.FloatTensor(10, 2).random_(8)
criterion = torch.nn.MSELoss(reduce=True, size_average=True)

for i in range(2):
    optimizer.zero_grad()     
    output = net(input_data)   
    loss = criterion(output, target)
    loss.backward()             
    optimizer.step()           
    print(list(net.parameters()))

輸出結(jié)果

tensor([1.], requires_grad=True)]
[Parameter containing:
tensor([0.9979], requires_grad=True)]
[Parameter containing:
tensor([0.9958], requires_grad=True)]

會更新~

以上為個人經(jīng)驗，希望能給大家一個參考，也希望大家多多支持腳本之家。

相關(guān)文章

最新評論