一、准备数据集
import torchvision
#准备数据集
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)
#lenth 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))
准备了数据集并加载了长度
二、利用DataLoader,来加载数据集
#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)
三、搭建网络模型
import torch
from torch import nn
#搭建网络模型
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, padding=2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(1024, 64),
nn.Linear(64, 10)
)
def forward(self,x):
x = self.model(x)
return x
#测试网络的正确性
if __name__ == '__main__':
tudui = Tudui()
input = torch.ones((64,3,32,32)) #设定一个输入的尺寸,64 barch_size, 3 通道,32*32
output = tudui(input)
print(output.shape)
网络模型可以单独放在一个Python文件中,只需在原来的文件中import一下,例如将网络模型的Python文件名命名为model,在原来的Python文件中 from model import *
注意这两个文件需要在同一个路径下
网络模型下面可以测试网络的正确性
返回64行数据, 每行数据有10个
四、创建网络模型
五、损失函数
六、优化器
#优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
七、设置训练网络的一些参数
#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("-------第{}轮训练开始-------".format(i+1))
#训练步骤开始
for data in train_dataloader:
imgs,targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
#优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
print("训练次数:{},Loss:{}".format(total_train_step,loss.item()))
运行结果
测试步骤
#测试步骤开始
total_test_loss = 0
with torch.no_grad():
for data in test_dataloader :
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
total_test_loss = total_test_loss + loss.item()
print("整体测试集上的Loss:{}".format(total_test_loss))
结果
用tensorboard可视化
#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
for data in train_dataloader:
imgs,targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
#优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
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
total_test_loss = 0
with torch.no_grad():
for data in test_dataloader :
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
total_test_loss = total_test_loss + loss.item()
print("整体测试集上的Loss:{}".format(total_test_loss))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
total_test_step = total_train_step + 1
writer.close()
可清晰地看到训练跟测试的损失都在 减小
保存
完整代码
train.py
import torchvision
from torch.utils.tensorboard import SummaryWriter
from model import *
from torch.utils.data import DataLoader
#准备数据集
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)
#lenth 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
tudui = Tudui()
#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
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 = 10
#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
for data in train_dataloader:
imgs,targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
#优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
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
total_test_loss = 0
with torch.no_grad():
for data in test_dataloader :
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs,targets)
total_test_loss = total_test_loss + loss.item()
print("整体测试集上的Loss:{}".format(total_test_loss))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
total_test_step = total_train_step + 1
torch.save(tudui,"tudui_{}.pth".format(i)) #保存每一轮的训练结果
print("模型已保存")
writer.close()
model.py
import torch
from torch import nn
#搭建网络模型
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5,1, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5,1,padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5,1, padding=2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(1024, 64),
nn.Linear(64, 10)
)
def forward(self,x):
x = self.model(x)
return x
#测试网络的正确性
if __name__ == '__main__':
tudui = Tudui()
input = torch.ones((64,3,32,32)) #设定一个输入的尺寸,64 barch_size, 3 通道,32*32
output = tudui(input)
print(output.shape)