Task5.PyTorch实现L1，L2正则化以及Dropout

1.了解知道Dropout原理　　

　　深度学习网路中，参数多，可能出现过拟合及费时问题。为了解决这一问题，通过实验，在2012年，Hinton在其论文《Improving neural networks by preventing co-adaptation of feature detectors》中提出Dropout。证明了其能有效解决过拟合的能力。

dropout 是指在深度学习网络的训练过程中，按照一定的概率将一部分神经网络单元暂时从网络中丢弃，相当于从原始的网络中找到一个更瘦的网络示意图如下：

　　其实现是以某种概率分布使得一些神经元为0，一些为1.这样在有N个神经元的神经网络中，其参数搭配可能有2^N种。
具体介绍 见论文（我也不是很懂 实现得见）
适用情况：
1 Dropout主要用在数据量不够，容易过拟合，需要dropout。

L1及L2可以使得结构化风险最小
其中：
L1的参数具有稀疏性（具有更多的0或1）
L2的参数趋近于分散化 ，其参数值趋向于选择更简单（趋于0的参数），因此比较平滑

2.用代码实现正则化(L1、L2、Dropout）

L1范数

　　L1范数是参数矩阵W中元素的绝对值之和，L1范数相对于L0范数不同点在于，L0范数求解是NP问题，而L1范数是L0范数的最优凸近似，求解较为容易。L1常被称为LASSO.

regularization_loss = 0
for param in model.parameters():
    regularization_loss += torch.sum(abs(param))

for epoch in range(EPOCHS):
    y_pred = model(x_train)
    classify_loss = criterion(y_pred, y_train.float().view(-1, 1))
    loss = classify_loss + 0.001 * regularization_loss  # 引入L1正则化项

L2范数

　　L2范数是参数矩阵W中元素的平方之和，这使得参数矩阵中的元素更稀疏，与前两个范数不同的是，它不会让参数变为0，而是使得参数大部分都接近于0。L1追求稀疏化，从而丢弃了一部分特征（参数为0），而L2范数只是使参数尽可能为0，保留了特征。L2被称为Rigde.

criterion  = torch.nn.BCELoss() #定义损失函数
optimizer = torch.optim.SGD(model.parameters(),lr = 0.01, momentum=0, dampening=0,weight_decay=0) #weight_decay 表示使用L2正则化

3.Dropout的numpy实现

import numpy as np

X = np.array([ [0,0,1],[0,1,1],[1,0,1],[1,1,1] ])

y = np.array([[0,1,1,0]]).T

alpha,hidden_dim,dropout_percent,do_dropout = (0.5,4,0.2,True)

synapse_0 = 2*np.random.random((3,hidden_dim)) - 1

synapse_1 = 2*np.random.random((hidden_dim,1)) - 1

for j in xrange(60000):

    layer_1 = (1/(1+np.exp(-(np.dot(X,synapse_0)))))

    if(do_dropout):

        layer_1 *= np.random.binomial([np.ones((len(X),hidden_dim))],1-dropout_percent)[0] * (1.0/(1-dropout_percent))

    layer_2 = 1/(1+np.exp(-(np.dot(layer_1,synapse_1))))

    layer_2_delta = (layer_2 - y)*(layer_2*(1-layer_2))

    layer_1_delta = layer_2_delta.dot(synapse_1.T) * (layer_1 * (1-layer_1))

    synapse_1 -= (alpha * layer_1.T.dot(layer_2_delta))

    synapse_0 -= (alpha * X.T.dot(layer_1_delta))

4.完整代码

import torch
from torch import nn
from torch.autograd import Variable
import torch.nn.functional as F
import torch.nn.init as init
import math
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import numpy as np
import pandas as pd
%matplotlib inline

# 导入数据
data = pd.read_csv(r'C:UsersettyDesktoppytorch学习data.txt')
x, y = data.ix[:,:8],data.ix[:,-1]

#测试集为30%，训练集为80%
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

x_train = Variable(torch.from_numpy(np.array(x_train)).float())
y_train = Variable(torch.from_numpy(np.array(y_train).reshape(-1, 1)).float())    

x_test = Variable(torch.from_numpy(np.array(x_test)).float())
y_test= Variable(torch.from_numpy(np.array(y_test).reshape(-1,1)).float())    


print(x_train.data.shape)
print(y_train.data.shape)

print(x_test.data.shape)
print(y_test.data.shape)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.l1 = torch.nn.Linear(8, 200)
        self.l2 = torch.nn.Linear(200, 50)
        self.l3 = torch.nn.Linear(50, 1)

    def forward(self, x):
        out1 = F.relu(self.l1(x))
        out2 = F.dropout(out1, p= 0.5)
        out3 = F.relu(self.l2(out2))
        out4 = F.dropout(out3, p=0.5)
        y_pred = F.sigmoid(self.l3(out3))
        return y_pred

model = Model()

criterion = torch.nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001, weight_decay=0.1)

Loss=[]
for epoch in range(2000):
        y_pred = model(x_train)
        loss = criterion(y_pred, y_train)
        if epoch % 400 == 0:
            print("epoch =", epoch, "loss", loss.item())
            Loss.append(loss.item())
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

# 模型评估
def label_flag(data):
    for i in range(len(data)):
        if(data[i]>0.5):
            data[i] = 1.0
        else:
            data[i] = 0.0
    return data

y_pred = label_flag(y_pred)  
print(classification_report(y_train.detach().numpy(), y_pred.detach().numpy()))

# 测试
y_test_pred = model(x_test)
y_test_pred = label_flag(y_test_pred)       
print(classification_report(y_test.detach().numpy(), y_test_pred.detach().numpy()))

数据集下载链接：链接：https://pan.baidu.com/s/1LrJktjVQ1OM9mYt_cuE-FQ
提取码：hatv

原文链接：https://blog.csdn.net/wehung/article/details/89283583