文章目录
- CIFAR10数据集简介
- 训练模型套路
- 1、准备数据集
- 2、加载数据集
- 3、搭建神经网络
- 4、创建网络模型、定义损失函数、优化器
- 5、训练网络
- 6、测试数据集
- 7、添加tensorboard
- 8、转化为正确率
- 9、保存模型
- 完整代码
本文以 CIFAR10数据集为例,介绍一个完整的模型训练套路。
CIFAR10数据集简介
CIFAR-10数据集包含60000张32x32彩色图像,分为10个类,每类6000张。有50000张训练图片和10000张测试图片。
数据集分为五个训练batches和一个测试batch,每个batch有10000张图像。测试batch包含从每个类中随机选择的1000个图像。训练batches以随机顺序包含剩余的图像,但有些训练batches可能包含一个类的图像多于另一个类的图像。在它们之间,训练batches包含来自每个类的5000张图像。
下面是数据集中的类,以及每个类的10张随机图片:
一共包含10 个类别的RGB 彩色图片:飞机( airplane )、汽车( automobile )、鸟类( bird )、猫( cat )、鹿( deer )、狗( dog )、蛙类( frog )、马( horse )、船( ship )和卡车( truck )。
训练模型套路
1、准备数据集
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="./source", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="./source", train=False, transform=torchvision.transforms.ToTensor(), download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print(f"训练数据集的长度为:{train_data_size}")
print(f"测试数据集的长度为:{test_data_size}")
2、加载数据集
# 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)
3、搭建神经网络
我们准备搭建一个这样的网络模型结构:
# 搭建神经网络
class Aniu(nn.Module):
def __init__(self):
super(Aniu, 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
if __name__ == '__main__':
aniu = Aniu()
input = torch.ones((64, 3, 32, 32))
output = aniu(input)
print(output.shape)
我们在一个新的文件下搭建并简单测试神经网络。
4、创建网络模型、定义损失函数、优化器
# 创建网络模型
aniu = Aniu()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(aniu.parameters(), lr=learning_rate)
5、训练网络
# 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 = 10
for i in range(epoch):
print(f"----------第{i+1}轮训练开始-----------")
# 训练开始
for data in train_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
# 优化器优化模型
optimizer.zero_grad() # 优化器梯度清零
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
print(f"训练次数:{total_train_step},loss:{loss.item()}") # .item()可以将tensor数据类型转化
6、测试数据集
我们可以通过with torch.mo_grad():
来测试
for i in range(epoch):
print(f"----------第{i+1}轮训练开始-----------")
# 训练开始
for data in train_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
# 优化器优化模型
optimizer.zero_grad() # 优化器梯度清零
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print(f"训练次数:{total_train_step},loss:{loss.item()}") # .item()可以将tensor数据类型转化
# 测试步骤开始
total_test_loss = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
total_test_loss = total_test_loss + loss.item()
print(f"整体测试集上的Loss:{total_test_loss}")
7、添加tensorboard
我们在以上的代码基础上添加tensorboard,并通过tensorboard画图进行观察:
# 添加tensorboard
writer = SummaryWriter("./log_train")
for i in range(epoch):
print(f"----------第{i+1}轮训练开始-----------")
# 训练开始
for data in train_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
# 优化器优化模型
optimizer.zero_grad() # 优化器梯度清零
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print(f"训练次数:{total_train_step},loss:{loss.item()}") # .item()可以将tensor数据类型转化
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
total_test_loss = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
total_test_loss = total_test_loss + loss.item()
print(f"整体测试集上的Loss:{total_test_loss}")
writer.add_scalar("test_loss", total_test_loss, total_test_step)
total_test_step = total_test_step + 1
writer.close()
运行并在终端输入:
tensorboard --logdir="log_train"
可以观察到图像:
8、转化为正确率
添加一段代码,算出测试集上的正确率:
# 整体正确的个数
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
output = aniu(imgs)
loss = loss_fn(output, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (output.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print(f"整体测试集上的Loss:{total_test_loss}")
print(f"整体测试集上的正确率:{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
9、保存模型
每轮保存一下模型:
torch.save(aniu, f"aniu_{i}.pth")
print("模型已保存")
完整代码
train.py文件:
import torch.cuda
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="./source", train=True,
transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="./source", train=False,
transform=torchvision.transforms.ToTensor(), download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print(f"训练数据集的长度为:{train_data_size}")
print(f"测试数据集的长度为:{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 搭建神经网络
class Aniu(nn.Module):
def __init__(self):
super(Aniu, 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
aniu = Aniu()
# if torch.cuda.is_available():
# aniu = aniu.cuda()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# if torch.cuda.is_available():
# loss_fn = loss_fn.cuda()
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(aniu.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 = 10
# 添加tensorboard
writer = SummaryWriter("./log_train")
for i in range(epoch):
print(f"----------第{i+1}轮训练开始-----------")
# 训练开始
aniu.train()
for data in train_dataloader:
imgs, targets = data
# if torch.cuda.is_available():
# imgs = imgs.cuda()
# targets = targets.cuda()
output = aniu(imgs)
loss = loss_fn(output, targets)
# 优化器优化模型
optimizer.zero_grad() # 优化器梯度清零
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print(f"训练次数:{total_train_step},loss:{loss.item()}") # .item()可以将tensor数据类型转化
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
aniu.eval()
total_test_loss = 0
# 整体正确的个数
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
# if torch.cuda.is_available():
# imgs = imgs.cuda()
# targets = targets.cuda()
output = aniu(imgs)
loss = loss_fn(output, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (output.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print(f"整体测试集上的Loss:{total_test_loss}")
print(f"整体测试集上的正确率:{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(aniu.state_dict(), f"aniu_{}.pth") 官方推荐保存方式
torch.save(aniu, f"aniu_{i}.pth")
print("模型已保存")
writer.close()
model.py:
import torch
from torch import nn
# 搭建神经网络
class Aniu(nn.Module):
def __init__(self):
super(Aniu, 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
if __name__ == '__main__':
aniu = Aniu()
input = torch.ones((64, 3, 32, 32))
output = aniu(input)
print(output.shape)