Pytorch 模型训练入门
定义是否使用GPU
可有可无，默认为 cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
训练数据：
BATCH_SIZE = 64 ：批处理尺寸，即一次处理图像的张数
加载训练数据 ： 以cifar10 为例
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform_train) #训练数据集
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2) #生成一个个batch进行批训练，组成batch的时候顺序打乱取
数据预处理（transform）
做一些增强，旋转，缩放，仿射变换等
测试数据：
加载测试数据 ： 以cifar10 为例
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
模型加载
现在模型文件定义好模型网络结构，以ResNet-34为例：
model = ResNet_34()
net = model.to(device)
定义损失函数和优化方式
#损失函数为交叉熵，多用于多分类问题
criterion = nn.CrossEntropyLoss()
#优化方式为mini-batch momentum-SGD，并采用L2正则化（权重衰减）
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4)
def adj_lr(optimizer):
for param_group in optimizer.param_groups:
param_group['lr'] = param_group['lr'] * 0.1
训练过程
for epoch in range(pre_epoch, EPOCH):
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device) # 加载数据
optimizer.zero_grad() #梯度清零
outputs = net(inputs) #数据过网络
loss = criterion(outputs, labels) #计算loss
loss.backward() #反向传播
optimizer.step() #更新参数
模型保存
torch.save(model,"resnet34-1-cifar.pkl")
torch.save(model.state_dict(),"resnet34-1-cifar-param.pkl")
总代码
#！ --*-- coding:utf-8 --*--
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import argparse
from resnet import ResNet18
from resnet_2 import ResNet_34
# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print "used device = " , device
# 参数设置,使得我们能够手动输入命令行参数，就是让风格变得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--outf', default='./model/', help='folder to output images and model checkpoints') #输出结果保存路径
parser.add_argument('--net', default='./model/Resnet18.pth', help="path to net (to continue training)") #恢复训练时的模型路径
args = parser.parse_args()
# 超参数设置
EPOCH = 64 #遍历数据集次数
pre_epoch = 0 # 定义已经遍历数据集的次数
BATCH_SIZE = 64 #批处理尺寸(batch_size)
LR = 0.1 #学习率
#LR = LR*gamma**epoch
# 准备数据集并预处理
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4), #先四周填充0，在吧图像随机裁剪成32*32
transforms.RandomHorizontalFlip(), #图像一半的概率翻转，一半的概率不翻转
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), #R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform_train) #训练数据集
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2) #生成一个个batch进行批训练，组成batch的时候顺序打乱取
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
# Cifar-10的标签
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
# 模型定义-ResNet
#model = ResNet18()
model = ResNet_34()
net = model.to(device)
# 定义损失函数和优化方式
#损失函数为交叉熵，多用于多分类问题
criterion = nn.CrossEntropyLoss()
#优化方式为mini-batch momentum-SGD，并采用L2正则化（权重衰减）
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4)
def adj_lr(optimizer):
for param_group in optimizer.param_groups:
param_group['lr'] = param_group['lr'] * 0.1
# 训练
if __name__ == "__main__":
best_acc = 85 #2 初始化best test accuracy
print("Start Training, Resnet-18!") # 定义遍历数据集的次数
for epoch in range(pre_epoch, EPOCH):
if(epoch in [8,16,32]):
adj_lr(optimizer)
net.train()
sum_loss = 0.0
correct = 0.0
total = 0.0
for i, data in enumerate(trainloader, 0):
# 准备数据
length = len(trainloader)
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad() #梯度清零
outputs = net(inputs) #数据过网络
loss = criterion(outputs, labels) #计算loss
loss.backward() #反向传播
optimizer.step() #更新参数
# 每训练1个batch打印一次loss和准确率
sum_loss += loss.item()
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += predicted.eq(labels.data).cpu().sum()
print('[epoch:%d, iter:%d] Loss: %.03f | Acc: %.3f%% '
% (epoch + 1, (i + 1 + epoch * length), sum_loss / (i + 1), 100. * correct / total))
# 每训练完一个epoch测试一下准确率
print("Waiting Test!")
with torch.no_grad(): # 不更新参数
correct = 0
total = 0
for data in testloader:
net.eval()
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
# 取得分最高的那个类 (outputs.data的索引号)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('测试分类准确率为：%.3f%%' % (100 * correct / total))
print('Saving model......')
torch.save(net.state_dict(), '%s/net_%03d.pth' % (args.outf, epoch + 1))
print("Training Finished, TotalEPOCH=%d" % EPOCH)
###save model
torch.save(model,"resnet34-1-cifar.pkl")
torch.save(model.state_dict(),"resnet34-1-cifar-param.pkl")