9、在多分类任务实验中手动实现dropout
import torch
import torch.nn as nn
import numpy as np
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
#读取数据
mnist_train = torchvision.datasets.MNIST(root='./data', train=True, download=False, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.MNIST(root='./data', train=False,download=False, transform=transforms.ToTensor())
batch_size = 256
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True,num_workers=0)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False,num_workers=0)
#初始化参数
num_inputs,num_hiddens,num_outputs =784, 256,10
num_epochs=30
lr = 0.001
def init_param():
W1 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens,num_inputs)), dtype=torch.float32)
b1 = torch.zeros(1, dtype=torch.float32)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_outputs,num_hiddens)), dtype=torch.float32)
b2 = torch.zeros(1, dtype=torch.float32)
params =[W1,b1,W2,b2]
for param in params:
param.requires_grad_(requires_grad=True)
return W1,b1,W2,b2
#手动定义dropout函数
def dropout(X, drop_prob): #drop_porb是一个概率值,介于0-1,代表要丢弃多少比例的神经元
X = X.float()
assert 0 <= drop_prob <= 1
keep_prob = 1 - drop_prob
if keep_prob == 0:
return torch.zeros_like(X)
mask = (torch.rand(X.shape) < keep_prob).float()
return mask * X / keep_prob
#定义模型
def net(X, is_training=True):
X = X.view(-1, num_inputs)
H1 = (torch.matmul(X, W1.t()) + b1).relu()
if is_training: #只有在训练模式下才需要dropout,测试情况下不需要
H1 = dropout(H1, drop_prob1)
return (torch.matmul(H1,W2.t()) + b2).relu()
#定义训练函数
def train(net,train_iter,test_iter,loss,num_epochs,batch_size,lr=None,optimizer=None):
train_ls, test_ls = [], []
for epoch in range(num_epochs):
ls, count = 0, 0
for X,y in train_iter:
l=loss(net(X),y)
optimizer.zero_grad()
l.backward()
optimizer.step()
ls += l.item()
count += y.shape[0]
train_ls.append(ls)
ls, count = 0, 0
for X,y in test_iter:
l=loss(net(X,is_training=False),y)
ls += l.item()
count += y.shape[0]
test_ls.append(ls)
if(epoch+1)%10==0:
print('epoch: %d, train loss: %f, test loss: %f'%(epoch+1,train_ls[-1],test_ls[-1]))
return train_ls,test_ls
#定义drop从0到1,训练十次,观察不同drop对结果的影响
drop_probs = np.arange(0,1.1,0.1)
Train_ls, Test_ls = [], []
#开始训练
for drop_prob in drop_probs:
drop_prob1 = drop_prob
W1,b1,W2,b2 = init_param()
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD([W1,b1,W2,b2],lr = 0.001)
train_ls, test_ls = train(net,train_iter,test_iter,loss,num_epochs,batch_size,lr,optimizer)
Train_ls.append(train_ls)
Test_ls.append(test_ls)
#结果可视化
x = np.linspace(0,len(train_ls),len(train_ls))
plt.figure(figsize=(10,8))
for i in range(0,len(drop_probs)):
plt.plot(x,Train_ls[i],label= 'drop_prob=%.1f'%(drop_probs[i]),linewidth=1.5)
plt.xlabel('epoch')
plt.ylabel('loss')
# plt.legend()
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),borderaxespad = 0.)
plt.title('train loss with dropout')
plt.show()
标签:torch,num,分类,dropout,手动,train,ls,test,drop
From: https://www.cnblogs.com/cyberbase/p/16821148.html