[人工智能]dropout代码（李沐动手学）

从零实现

import torch
from torch import nn
import matplotlib.pyplot as plt
from d2l import torch as d2l

def dropout_layer(X,dropout):
    assert 0<=dropout<=1
    if dropout==0:
        return torch.zeros_like(X)
    if dropout==1:
        return X
    mask=(torch.rand(X.shape)>dropout).float()
    return mask*X/(1.0-dropout)


t=torch.arange(16).reshape(2,8)
print(dropout_layer(t,0))
print(dropout_layer(t,0.2))
print(dropout_layer(t,0.5))
print(dropout_layer(t,0.7))
print(dropout_layer(t,1))

num_inputs,num_outputs,num_hiddens1,num_hiddens2=784,10,256,256
dropout1,dropout2=0.2,0.5
class Net(nn.Module):
    def __init__(self,num_inputs,num_outputs,num_hiddens1,num_hiddens2,is_training=True):
        super(Net,self).__init__()
        self.num_inputs=num_inputs
        self.training=is_training
        self.lin1=nn.Linear(num_inputs,num_hiddens1)
        self.lin2=nn.Linear(num_hiddens1,num_hiddens2)
        self.lin3=nn.Linear(num_hiddens2,num_outputs)
        self.relu=nn.ReLU()

    def forward(self,X):
        H1=self.relu(self.lin1(X.reshape(-1,self.num_inputs)))
        if self.training==True:
            H1=dropout_layer(H1,dropout1)
        H2=self.relu(self.lin2(H1))
        if self.training==True:
            H2=dropout_layer(H2,dropout2)
        out=self.lin3(H2)
        return out

net=Net(num_inputs,num_outputs,num_hiddens1,num_hiddens2)

num_epochs,lr,batch_size=10,0.5,256
loss=nn.CrossEntropyLoss()
train_iter,test_iter=d2l.load_data_fashion_mnist(batch_size)
trainer=torch.optim.SGD(net.parameters(),lr=lr)
d2l.train_ch3(net,train_iter,test_iter,loss,num_epochs,trainer)
plt.show()

简洁实现：

import torch
from torch import nn
import matplotlib.pyplot as plt
from d2l import torch as d2l
num_inputs,num_outputs,num_hiddens1,num_hiddens2=784,10,256,256
dropout1,dropout2=0.2,0.5
net=nn.Sequential(nn.Flatten(),
                  nn.Linear(num_inputs,num_hiddens1),nn.ReLU(),nn.Dropout(dropout1),
                  nn.Linear(num_hiddens1,num_hiddens2),nn.ReLU(),nn.Dropout(dropout2),
                  nn.Linear(num_hiddens2,num_outputs))

def init_weights(m):
    if type(m)==nn.Linear:
        nn.init.normal_(m.weight,0,0.01)

net.apply(init_weights)
num_epochs,lr,batch_size=10,0.5,256
loss=nn.CrossEntropyLoss()
train_iter,test_iter=d2l.load_data_fashion_mnist(batch_size)
trainer=torch.optim.SGD(net.parameters(),lr=lr)
d2l.train_ch3(net,train_iter,test_iter,loss,num_epochs,trainer)
plt.show()

从零实现：dropout1,dropout2=0.2,0.5
dropout1,dropout2=0.0,0.0

简洁实现：dropout1,dropout2=0.2,0.5

dropout1,dropout2=0.0,0.0

实验了多次，发现简洁实现中用不用dropout最终结果差不多，但是时间可能有区别，但是数据集比较小，区别也不明显

dropout1,dropout2=0.5,0.5

dropout1,dropout2=0.9,0.9

dropout1,dropout2=0.5,0.7