pytorch训练模板代码
一般分为以下六个步骤(个人习惯,仅供参考)
① 划分数据集
② 加载数据集
③数据集预处理
④搭建模型
⑤使用模型训练数据集
⑥根据训练结果考虑是否重复①~⑤
注意:
① model.train()和model.eval()的区别主要在于Batch Normalization和Dropout两层。
② 如果模型中有BN层(Batch Normalization)和 Dropout,需要在训练时添加model.train()。model.train()是保证BN层能够用到每一批数据的均值和方差。对于Dropout,model.train()是随机取一部分网络连接来训练更新参数。
③ 不启用 Batch Normalization 和 Dropout。
如果模型中有BN层(Batch Normalization)和Dropout,在测试时添加model.eval()。model.eval()是保证BN层能够用全部训练数据的均值和方差,即测试过程中要保证BN层的均值和方差不变。对于Dropout,model.eval()是利用到了所有网络连接,即不进行随机舍弃神经元。
④ 训练完train样本后,生成的模型model要用来测试样本。在model(test)之前,需要加上model.eval(),否则的话,有输入数据,即使不训练,它也会改变权值。这是model中含有BN层和Dropout所带来的的性质。
⑤ 在做one classification的时候,训练集和测试集的样本分布是不一样的,尤其需要注意这一点。
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter #tensorboard显示
# from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
# 定义训练的设备 gpu 适用对象 数据(非dataset)model loss
device = torch.device("cuda"if torch.cuda.is_available() else "cpu")
train_data = torchvision.datasets.CIFAR10(root="./data", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root="./data", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为:10
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))
# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
class MyModel(nn.Module):
def __init__(self):
super(MyModel, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64*4*4, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model(x)
return x
MyModel= MyModel()
MyModel= MyModel.to(device)
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 20
# 添加tensorboard
writer = SummaryWriter("./logs_train")
for i in range(epoch):
print("-------第 {} 轮训练开始-------".format(i+1))
# 训练步骤开始
MyModel.train()
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = MyModel(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad() #清理前一次梯度
loss.backward()#反向求导
optimizer.step()#更新网络数据
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print("训练次数:{}, Loss: {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
MyModel.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = MyModel(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum() #outputs.argmax(1) 横向比较 找出最大值的索引
total_accuracy = total_accuracy + accuracy
print("整体测试集上的Loss: {}".format(total_test_loss))
print("整体测试集上的正确率: {}".format(total_accuracy/test_data_size))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(MyModel, "res_model/myModel_{}.pth".format(i))
print("模型已保存")
writer.close()#关闭tensorborad