小土堆pytorch学习笔记005 | 完结，✿✿ヽ(°▽°)ノ✿
目录
1、损失函数与反向传播
2、如何在搭建的网络中使用损失函数呢？
3、优化器
4、现有网络模型的使用及修改
例子：
5、模型训练保存+读取
（1）保存
（2）读取
6、完整的模型训练：
（1）代码
【model文件】：
【主文件】：
（2）运行截图：
（3）绘图展示：
（4）添加训练正确率的完整代码：
（5）总结！！！：
（6）使用GPU训练
7、 完整模型验证
（1）代码
（2）运行结果
1、损失函数与反向传播
①计算实际输出和目标之间的差距。
②为我们更新输出提供一定的依据。（反向传播）
损失函数例子实战：
import torch
from torch import nn
from torch.nn import L1Loss
inputs = torch.tensor([1, 2, 3], dtype=torch.float32)
targets = torch.tensor([1, 2, 5], dtype=torch.float32)
inputs = torch.reshape(inputs, (1, 1, 1, 3)) # 1batch_size / 1channel / 1行3列
targets = torch.reshape(targets, (1, 1, 1, 3))
# loss = L1Loss(reduction='sum') # 损失，求和 (x-y)求和 结果：tensor(2.)
loss = L1Loss() # 损失，求mean() (x-y)求和/n 结果：tensor(0.6667)
result = loss(inputs, targets)
print("loss:",result)
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets) # 计算过程 (x-y)^2
print("mse_loss:", result_mse) # tensor(1.3333)
x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1,3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print("result_cross:",result_cross)
2、如何在搭建的网络中使用损失函数呢？
import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./test11_data", train=False,download=True,
transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = Sequential(
Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
MaxPool2d(2),
Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
MaxPool2d(2),
Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(in_features=1024, out_features=64),
Linear(in_features=64, out_features=10)
)
def forward(self, x):
x = self.model1(x)
return x
loss = nn.CrossEntropyLoss()
tudui = Tudui()
for data in dataloader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
result_loss.backward() # 反向传播
print(result_loss)
3、优化器
import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./test11_data", train=False,download=True,
transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = Sequential(
Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
MaxPool2d(2),
Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
MaxPool2d(2),
Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(in_features=1024, out_features=64),
Linear(in_features=64, out_features=10)
)
def forward(self, x):
x = self.model1(x)
return x
loss = nn.CrossEntropyLoss()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(), lr=0.01)
for epoch in range(20):
running_loss = 0.0
for data in dataloader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
optim.zero_grad() # 将梯度清零
result_loss.backward() # 调用反向传播
optim.step()
running_loss = running_loss + result_loss
print(running_loss)
4、现有网络模型的使用及修改
例子：
import torchvision
import ssl
from torch import nn
ssl._create_default_https_context = ssl._create_unverified_context
# train_data = torchvision.datasets.ImageNet("./test19_data",split='train',download=True,
# transform=torchvision.transforms.ToTensor())
vgg16_false = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print(vgg16_true)
train_data = torchvision.datasets.CIFAR10('./test13_data', train=True, download=True,
transform=torchvision.transforms.ToTensor())
# 在现有网络里面，添加一些东西
vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))
print(vgg16_true)
# 在现有网络里面，修改一些东西
print("修改之前vgg16_false:", vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096,10)
print("修改之后vgg16_false:", vgg16_false)
5、模型训练保存+读取
（1）保存
import torch
import torchvision
from torch import nn
vgg16 = torchvision.models.vgg16(pretrained=False)
# 保存方式1： 模型结构+模型参数
torch.save(vgg16, "vgg16_method1.pth")
# 保存方式2：模型参数（官方推荐的）
torch.save(vgg16.state_dict(), "vgg16_method2.pth")
# 陷阱
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
def forward(self, x):
x = self.conv1(x)
return x
tudui = Tudui()
torch.save(tudui, "tudui_method1.pth")（2）读取
import torch
import torchvision
from torch import nn
# 方式1：加载模型
model = torch.load("./vgg16_method1.pth")
# print(model)
# 方式2：加载模型
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("./vgg16_method2.pth"))
# print(vgg16)
# model2 = torch.load("./vgg16_method2.pth")
# print(model2)
# 陷阱1(需要将Tudui引入)
from test20_model_save import *
model_tudui = torch.load("./tudui_method1.pth")
print(model_tudui)6、完整的模型训练：
（1）代码
【model文件】：
import torch
from torch import nn
# 搭建神经网络
class Tudui(nn.Module):
def __init__(self):
super(Tudui, 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__':
tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)
【主文件】：
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from pytorch_xiaotudui.model import Tudui
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./test13_data", train=True, download=True,
transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./test13_data", train=False,download=True,
transform=torchvision.transforms.ToTensor())
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
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加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建神经网络
tudui = Tudui()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
learning_rate = 0.01 # 学习速率 或者写成 learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
total_train_step = 0 # 记录训练的参数
total_test_step = 0 # 记录测试的次数
epoch = 10 # 训练的轮数
# 添加tensorboard
writer = SummaryWriter("test22_logs")
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() # 将数据清零
loss.backward() # 反向传播
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
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_test_step+1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
（2）运行截图：
（3）绘图展示：
（4）添加训练正确率的完整代码：
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from pytorch_xiaotudui.model import Tudui
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./test13_data", train=True, download=True,
transform=torchvision.transforms.ToTensor())
test_data = torchvision.datasets.CIFAR10("./test13_data", train=False,download=True,
transform=torchvision.transforms.ToTensor())
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
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加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建神经网络
tudui = Tudui()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
learning_rate = 0.01 # 学习速率 或者写成 learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
total_train_step = 0 # 记录训练的参数
total_test_step = 0 # 记录测试的次数
epoch = 10 # 训练的轮数
# 添加tensorboard
writer = SummaryWriter("test22_logs")
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() # 将数据清零
loss.backward() # 反向传播
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
total_accuracy = 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()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
print("整体测试集上的Loss:{}".format(total_test_loss))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accauray", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step+1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
（5）总结！！！：
①创建dataset、dataloader加载数据
②搭建网络模型、创建网络模型实例
③定义损失函数
④定义优化器
⑤设置网络参数
⑥开始训练
⑦验证模型、保存模型
⑧将训练结果展示
（6）使用GPU训练
网络模型、数据（输入、标注）、损失函数 .cuda() 就可以。
如果自己笔记本上没有GPU的话，那么我们可以使用google提供的colab运行。（前提是要能访问上去，且要有个账号）。
界面有点儿类似，jupyter 那种。（部分截图如下， GPU跑的确实很快很快！！）
用GPU 跑完用时，1分钟45秒；用我的电脑，直接干到风扇转起来，呼呼响！！！
7、 完整模型验证
（1）代码
import torch
import torchvision.transforms
from PIL import Image
from torch import nn
image_path = "./imgs/airplane.png"
image = Image.open(image_path)
print(image) # PIL格式的图片
image = image.convert('RGB') # 因为png格式是4通道，除了RGB三通道外，还有一个透明度通道。
transforms = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
torchvision.transforms.ToTensor()])
image = transforms(image)
print(image) # tensor格式的图片
# 搭建神经网络
class Tudui(nn.Module):
def __init__(self):
super(Tudui, 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
model = torch.load("./tudui_9.pth", map_location=torch.device('cpu') )
print(model)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
output = model(image)
print(output)
print(output.argmax(1))
"""
数据：
class_to_idx:
0 airplane
1 automobile
2 bird
3 cat
4 deer
5 dog
6 frog
7 horse
8 ship
9 truck
"""
（2）运行结果
