import torch
from torch import nn
from d2l import torch as d2l
def dropout_layer(X,dropout):
assert 0<=dropout<=1
if dropout==1:
return torch.zeros_like(X)
if dropout==0:
return X
#mask=(torch.randn(X.shape)>dropout).float() 沐神手快敲错了
#rand和randn区别：https://blog.csdn.net/wangwangstone/article/details/89815661
mask = (torch.rand(X.shape) > dropout).float()
这里其实就相当于，在里面随机生成了一个矩阵，值为0-1的均匀分布，取里面大于dropout的值为1，在return中相乘就相当于保留下来，另外
dropout概率的那部分会因为不满足">"号取到false，也就是0，在return中相乘会直接舍去当时的值。
return mask*X/(1.0-dropout)
'''
便于你理解dropout里面那段函数
A=torch.tensor(\[1,2,3,4,5,6,7,8,9,10,11,12])
print(A)
B=torch.rand(A.shape)
print(B)
mask=(torch.rand(A.shape)>0.2).float()
print(mask)
'''
测试dropout_layer 函数
def test_dropout_layer():
X=torch.arange(16,dtype=torch.float32).reshape((2,8))
print(X)
print(dropout_layer(X,0))
print(dropout_layer(X, 0.5))
print(dropout_layer(X, 1))
test_dropout_layer()
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)
d2l.plt.show()
简洁实现
net=nn.Sequential(nn.Flatten(),nn.Linear(784,256),nn.ReLU(),nn.Dropout(dropout1),nn.Linear(256,256),nn.ReLU(),nn.Dropout(dropout2),nn.Linear(256,10))
def init_weights(m):
if type(m)==nn.Linear:
nn.init.normal_(m.weight,std=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)
d2l.plt.show()