Pytorch深度学习快速入门教程【小土堆Pytorch学习笔记】

七天七夜七斤作业

已于 2023-10-02 17:23:28 修改

阅读量910

点赞数 8

文章标签： pytorch 学习笔记

于 2023-09-28 20:19:42 首次发布

本文链接：https://blog.csdn.net/qq_54012756/article/details/133387451

版权

小土堆测pytorch学习笔记

一、Pytorch进行加载数据

在这里插入图片描述

Dateset:

提供一种方式去获取数据及其label。

主要涉及两个操作：1、如何获取每一个数据及其label 2、如何获取总共有多少个数据。

Dateloader:

为后面的网络提供不同的数据形式。

#加载数据集的代码
from torch.utils.data import Dataset
from PIL import Image
import os

class MyData(Dataset):

    def __init__(self, root_dir, label_dir):
        self.root_dir = root_dir
        self.label_dir = label_dir
        self.path = os.path.join(root_dir, label_dir)
        self.img_path = os.listdir(self.path)

    def __getitem__(self, idx):
        img_name = self.img_path[idx]
        img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
        img = Image.open(img_item_path)
        label = self.label_dir
        return img, label

    def __len__(self):
        return len(self.img_path)


root_dir = "dataset/train"
ants_label_dir = "ants"
bees_label_dir = "bees"
ants_dataset = MyData(root_dir, ants_label_dir)
bees_dataset = MyData(root_dir, bees_label_dir)

二、Tensorboard的使用

1、绘制曲线

from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter("logs")

# writer.add_image()
# y = x

for i in range(100):
    writer.add_scalar("y = 2x", 2 * i, i)

writer.close()

tensorboard --logdir=logs

亦可自己指定端口 tensorboard --logdir=logs --port=6007

2、打开图片

from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image

writer = SummaryWriter("logs")
image_path = "dataset/train/bees/29494643_e3410f0d37.jpg" #找到图片的相对路径
img_PIL = Image.open(image_path) 
img_array = np.array(img_PIL) # 将图片的格式转换为np.array()

writer.add_image("test", img_array, 2, dataformats='HWC') # 这里注意要声明图片的三个参数，这里是高宽和通道

writer.close()

三、Transforms的使用(主要对图片进行一些变化)

1、如何使用Transform

在这里插入图片描述

from torchvision import transforms
from PIL import Image

# python的用法
img_path = "dataset/train/ants/0013035.jpg"
img = Image.open(img_path)
print(img)

# 如何使用transform

tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)


print(tensor_img)

2、为什么需要Tensor的数据类型

from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
from PIL import Image

# python的用法
img_path = "dataset/train/ants/0013035.jpg"
img = Image.open(img_path)

writer = SummaryWriter("logs")

# 如何使用transform

tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)

writer.add_image("Tensor_img", tensor_img)

writer.close()

3、常见的Transforms

在这里插入图片描述

3、1 ToTensor的使用与Normalize(归一化)的使用

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

writer = SummaryWriter("logs")
img_path = "dataset/train/ants/0013035.jpg"
img = Image.open(img_path)
print(img)

# ToTensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)

#Normalize
print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([1, 3, 5], [0.5, 0.5, 0.5])
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize", img_norm, 1)

writer.close()

归一化的公式：
$o u tp u t [c hann e l] = (in p u t [c hann e l] - m e an [c hann e l]) / s t d [c hann e l]$

3、1 Resize、Compose与RanodmCrop的使用

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

writer = SummaryWriter("logs")
img_path = "dataset/train/ants/0013035.jpg"
img = Image.open(img_path)
print(img)

# ToTensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)

#Resize
print(img.size)
trans_resize = transforms.Resize((512, 512))
img_resize = trans_resize(img)
img_resize = trans_totensor(img_resize)
writer.add_image("Resize", img_resize, 0)
print(img_resize)

#Compose resize - 2
trans_resize_2 = transforms.Resize(512)
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Resize_2", img_resize_2, 1)

#RanodmCrop
trans_random = transforms.RandomCrop(512)
trans_compose_2 = transforms.Compose([trans_random, trans_totensor])
for i in range(10):
    img_crop = trans_compose_2(img)
    writer.add_image("RandomCrop", img_crop, i)

writer.close()

四、torchivision中的数据集的使用

import torchvision
from torch.utils.tensorboard import SummaryWriter

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])

train_set = torchvision.datasets.CIFAR10(root="./dataset1", train=True, transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset1", train=False, transform=dataset_transform,download=True)

print(test_set[0])
print(test_set.classes)

# img, target = test_set[0]
# print(img)
# print(target)
# print(test_set.classes[target])
# img.show()

# print(test_set[0])

writer = SummaryWriter("logs")
for i in range(10):
    img, target = test_set[i]
    writer.add_image("test_set", img, i)
writer.close()

五、DataLoader的使用

import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

# 准备的测试数据集
test_data = torchvision.datasets.CIFAR10("./dataset1", train=False, transform=torchvision.transforms.ToTensor())

test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True, num_workers=0, drop_last=True)
# 测试数据集中第一张图片及target
img, target = test_data[0]
print(img.shape)
print(target)

writer = SummaryWriter("logs")

for epoch in range(2):
    step = 0
    for data in test_loader: # batch_size=4的含义是以4为一组进行打包 shuffle是是否进行打乱 drop_last是最后剩余的余数是否进行舍去
        imgs, targets = data
        # print(imgs.shape)
        # print(targets)
        writer.add_images("Epoch: {}".format(epoch), imgs, step)
        step = step + 1

writer.close()

六、nn.Module的使用

在这里插入图片描述

import torch
from torch import nn


class Tudui(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, input):
        output = input + 1
        return output


tudui = Tudui()
x = torch.tensor(1.0)
output = tudui(x)
print(output)

七、神经网络

1、卷积层

卷积后的输出计算方式是：输入图像和卷积核的对应位相乘再相加
在这里插入图片描述

在这里插入图片描述

输入数据必须是四维的，所以用torch.reshape改变维度，bias是偏置，weight是卷积核，stride是步径，padding是边距

在这里插入图片描述

上图的是padding为1的输入图像，空白处默认为0

import torch
import torch.nn.functional as F
input = torch.tensor([[1, 2, 0, 3, 1],
                      [0, 1, 2, 3, 1],
                      [1, 2, 1, 0, 0],
                      [5, 2, 3, 1, 1],
                      [2, 1, 0, 1, 1]])

kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])

input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

print(input.shape)
print(kernel.shape)

output = F.conv2d(input, kernel, stride=1)
print(output)

output2 = F.conv2d(input, kernel, stride=2)
print(output2)

output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)

在这里插入图片描述

常用的前五个参数，输入通道数，输出通道数，卷积核的大小，步径，边距

在这里插入图片描述

输入通道数为1，输出通道数为2的时候，卷积核应该有两个。

一个重要的计算，维持图像的尺寸：

在这里插入图片描述

import torch
import torchvision
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch import nn
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),
                                       download=True)

dataloader = DataLoader(dataset, batch_size=64)

class TuDui(nn.Module):
    def __init__(self):
        super(TuDui, self).__init__()
        self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)

    def forward(self, x):
        x = self.conv1(x)
        return x

tudui = TuDui()
print(tudui)

writer = SummaryWriter("../logs")
step = 0
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    print(imgs.shape)
    print(output.shape)

    writer.add_images("input", imgs, step)

    output = torch.reshape(output, (-1, 3, 30, 30))
    writer.add_images("output", output, step)

    step = step + 1

writer.close()

2、池化层

作用：降低参数的数量，但保持输入数据的主要特征
在这里插入图片描述

参数含义：池化核的大小

步径，默认值为池化核的大小

边距

偏置，空洞

无需了解

ceil是保留，floor是舍弃

在这里插入图片描述

import torch
from torch import nn
from torch.nn import MaxPool2d

input = torch.tensor([[1, 2, 0, 3, 1],
                      [0, 1, 2, 3, 1],
                      [1, 2, 1, 0, 0],
                      [5, 2, 3, 1, 1],
                      [2, 1, 0, 1, 1]], dtype=torch.float32)
input = torch.reshape(input, (-1, 1, 5, 5))
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)

    def forward(self, input):
        output = self.maxpool1(input)
        return output

tudui = Tudui()
output = tudui(input)
print(output)

3、非线性激活

目的：在网络中引入更多的非线性特征

在这里插入图片描述

inplace含义是是否替换原数据

import torch
from torch import nn
from torch.nn import ReLU

input = torch.tensor([[1, -0.5],
                      [-1, 3]])

input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.relu1 = ReLU()

    def forward(self, input):
        output = self.relu1(input)
        return output

tudui = Tudui()
output = tudui(input)
print(output)

4、线性层及其他层

在这里插入图片描述

5、搭建简易网络模型

目标：CIFAR 10 model结构
在这里插入图片描述

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x

tudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)


writer = SummaryWriter("../logs_seq")
writer.add_graph(tudui, input)
writer.close()

6、损失函数与反向传播

LossFunction的作用：（一定注意LossFunction的输入）

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）]

L1Loss的计算：
在这里插入图片描述

import torch
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))
targets = torch.reshape(targets, (1, 1, 1, 3))

loss = L1Loss(reduction="sum")
res = loss(inputs, targets)
print(res)

MSELoss(平方差)

loss_mse = nn.MSELoss()
res_mse = loss_mse(inputs, targets)

CrossEntropyLoss(交叉熵)

在这里插入图片描述

x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()
res_cross = loss_cross(x, y)
print(res_cross)

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=
                                       True)
dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 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)
    res_loss = loss(outputs, targets)
    print(res_loss)

7、优化器

# 使用随机梯度下降的优化器
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=
                                       True)
dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 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)
        res_loss = loss(outputs, targets)
        optim.zero_grad() # 梯度清零
        res_loss.backward() # 反向传播求出每个点的梯度
        optim.step() # 对每个参数进行调优
        running_loss = running_loss + res_loss
    print(running_loss)

8、现有网络模型的使用及修改

import torchvision
from torch import nn

vgg16_flase = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print(vgg16_true)

train_data = torchvision.datasets.CIFAR10("../data", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)

vgg16_true.classifier.add_module("add_linear", nn.Linear(1000, 10)) # 添加模型
print(vgg16_true)

vgg16_flase.classifier[6] = nn.Linear(4096, 10)
print(vgg16_flase)

9、网络模型的保存与读取

model_sava.py

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）
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")

model_load.py

import torch
import torchvision
from torch import nn
from model_save import *

# 保存方式1，加载模型
model = torch.load("vgg16_method1.pth")
# print(model)


#保存方式2， 加载模型
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
# print(vgg16)


# 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
model = torch.load("tudui_method1.pth")
print(model)

八、完整的模型训练套路

train.py

import torchvision
from torch.utils.tensorboard import SummaryWriter

from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

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
tudui = Tudui()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 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
    tudui.train()
    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
    tudui.eval()
    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(tudui, "tudui_{}.pth".format(i))
    print("模型已保存")

writer.close()

model.py

import torch
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear


# 搭建神经网络
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x


if __name__ == '__main__':
    tudui = Tudui()
    input = torch.ones((64, 3, 32, 32))
    output = tudui(input)
    print(output.shape)

九、利用GPU训练

在这里插入图片描述

方式1

import torch
import torchvision
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter

# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

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 Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x
tudui = Tudui()
if torch.cuda.is_available():
    tudui = tudui.cuda()

# 损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

# 优化器
# learning_rate = 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
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        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
    tudui.eval()
    total_test_loss = 0
    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()
            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(tudui, "tudui_{}.pth".format(i))
    print("模型已保存")

writer.close()

方式2

import torch
import torchvision
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter

# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

# 定义训练的设备
device = torch.device("cuda:0")

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 Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x
tudui = Tudui()
tudui.to(device)

# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn.to(device)

# 优化器
# learning_rate = 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
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        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
    tudui.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 = 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(tudui, "tudui_{}.pth".format(i))
    print("模型已保存")

writer.close()

十、模型验证套路

import torch
import torchvision
from PIL import Image
from torch import nn

image_path = "../imgs/airplane.png"
image = Image.open(image_path)
print(image)
image = image.convert('RGB')
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
                                            torchvision.transforms.ToTensor()])

image = transform(image)
print(image.shape)

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_29_gpu.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))

import torch
import torchvision
from PIL import Image
from torch import nn

image_path = "../imgs/airplane.png"
image = Image.open(image_path)
print(image)
image = image.convert('RGB')
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
                                            torchvision.transforms.ToTensor()])

image = transform(image)
print(image.shape)

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_29_gpu.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))