13丢弃法

点击查看代码

import time

import torch
from torch import nn
from d2l import torch as d2l

# 丢弃法：层之间加噪音
# 通常将丢弃法作用在隐藏全连接层的输出上
"""
丢弃法将一些输出项随机置0来控制模型复杂度
常作用在多层感知机的隐藏层输出上
丢弃概率是控制模型复杂度的超参数
"""

# 以dropout的概率丢弃张量输入X中的元素
def dropout_layer(X, dropout):
    assert 0 <= dropout <= 1
    if dropout == 1:
        return torch.zeros_like(X)
    if dropout == 0:
        return X
    # 随机生成的数与dropout相比，生成0/1
    mask = (torch.randn(X.shape) > dropout).float()
    return mask * X / (1.0 - dropout)

# 测试dropout_layer函数
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))

# 定义具有两个隐藏层的多层感知机，每个隐藏层包含256个单元
"""
num_outputs        10
num_hiddens2      256
num_hiddens1      256
num_inputs        784
"""
num_outputs = 10
num_hiddens2 = 256
num_hiddens1 = 256
num_inputs = 784
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)
# 训练
# time1 = time.time()
num_epochs, lr, batch_size = 3, 0.5, 256
loss = nn.CrossEntropyLoss()
train_iter, valid_iter = d2l.load_data_fashion_mnist(batch_size)
trainer = torch.optim.SGD(net.parameters(), lr=lr)
# d2l.train_ch3(net, train_iter, valid_iter, loss, num_epochs, trainer)
# print(time.time()-time1)

# 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, 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)

time1 = time.time()
trainer = torch.optim.SGD(net.parameters(), lr=lr)
d2l.train_ch3(net, train_iter, valid_iter, loss, num_epochs, trainer)
print(time.time()-time1)

----------------