李沐深度学习-ch4 dropout 暂退法

#dropout
import torch
from torch import nn
from d2l import torch as d2l
def dropout_layer(X, dropout):
 # X is input vector and dropout is proability. the fun gives a randomly vector from uniform distribution on [0, 1] shaped like X and if the value < dropout drop it else change it into x/(1-dropout)
 assert 0 error
 if dropout == 1:
 return torch.zeros_like(X)
 if dropout == 0:
 return X
 mask = (torch.rand(X.shape) > dropout).float()
 return mask * X / (1.0 - dropout)
dropout1, dropout2 = 0.2, 0.5
num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256
class Net(nn.Module):
 def __init__(self, num_inputs, num_outputs, num_hiddens1, num_hiddens2, is_training):
 super(Net, self).__init__()
 self.num_inputs = num_inputs
 #self.num_outputs = num_outputs
 #self.num_hiddens1 = num_hiddens1
 #self.num_hiddens2 = num_hiddens2
 self.is_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.is_training == True:
 H1 = dropout_layer(H1, dropout1)
 H2 = self.relu(self.lin2(H1))
 if self.is_training == True:
 H2 = dropout_layer(H2, dropout2)
 return self.lin3(H2)
net_train = Net(num_inputs, num_outputs, num_hiddens1, num_hiddens2, True)
num_epochs, lr, batch_size = 10, 0.5, 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
loss = nn.CrossEntropyLoss(reduction="none")
trainer = torch.optim.SGD(net_train.parameters(), lr)
d2l.train_ch3(net_train, train_iter, test_iter, loss, num_epochs, trainer)
作者:Presence、原文地址:https://blog.csdn.net/weixin_44012124/article/details/127949934

%s 个评论

要回复文章请先登录注册