PyTorch深度学习快速入门教程（绝对通俗易懂！！！）

---

一、PyTorch环境的配置及安装

1.官网下载最新版Anaconda，完成后打开Anaconda Prompt，显示（base）即安装成功
2.conda create -n pytorch python=3.6建立一个命名为pytorch的环境，且环境python版本为3.6
3.conda activate pytorch激活并进入pytorch这个环境;linux：source activate pytorch
4.pip list来查看环境内安装了哪些包，可以发现并没有我们需要的pytorch
5.打开PyTorch官网，直接找到最新版pytorch指令conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch（无脑最新版就完事了。。。。老版本调了半天，最后还出问题了），打开pytorch环境，输入指令下载安装
6.检验是否安装成功。输入python，import torch不报错即pytorch安装成功。输入torch.cuda.is_available(),若返回True即机器显卡是可以被pytorch使用的（如失败，建议去英伟达官网下载更新驱动程序，并删除环境，使用各种最新版重新安装）。
7.linux服务器安装时出现环境安装不到conda/envs下，而在.conda下，进行如下操作

other:conda info -e （查看所有的虚拟环境）
rm -rf + 文件名 删除文件夹
df -h查看linux系统各分区的情况
nohup 命令 > 文件 2>&1 & # 使模型在后台训练 exit退出黑窗口
1.> 会重写文件，如果文件里面有内容会覆盖，没有则创建并写入。
2.>> 将内容追加到文件中，即如果文件里面有内容会把新内容追加到文件尾，如果文件不存在，就创建文件
kill -9 PID # 关闭特定进程
tar -xvf #解压tar包
查看当前文件夹的大小：du -ah
查看当前文件夹下面各个文件夹的大小：du -ah --max-depth=1
anaconda下的pkgs怎么清理:conda clean -a
ps -aux 查询内存中进程信息；
ps -aux | grep *** 查询***进程的详细信息；

二、Pycharm、jupyter的安装

1. Pycharm

1.pycharm官网下载安装
2.新建项目（lean_pytorch)，
点击已存在的编译器，点进去寻找刚刚我们安装好的环境。
导入成功。

2.jupyter

1. 安装好anaconda后无需再次安装。
2. jupyter默认安装在base环境中，所以我们需要在pytorch环境中安装jupyter.
3. 进入pytorch环境，输入conda install nb_conda安装juypter
4. 安装完成后输入juypter notebook即可打开。
5. 
   新建pytorch环境下的juypter文件。
6. 输入import torch,torch.cuda.is_available()，返回TRUE即安装成功。

三、Python学习中的两大法宝函数（help、dir）

进入pycharm的python console，输入dir(torch),dir(torch.cuda),dir(torch.cuda.is_available()),help(torch.cuda.is_available)。

四、加载数据（Dataset）

from torch.utils.data import Dataset, DataLoader
import numpy as np
from PIL import Image
import os
from torchvision import transforms
from torch.utils.tensorboard import SummaryWriter
from torchvision.utils import make_grid

writer = SummaryWriter("logs")

class MyData(Dataset):

    def __init__(self, root_dir, image_dir, label_dir, transform):
        self.root_dir = root_dir
        self.image_dir = image_dir
        self.label_dir = label_dir
        self.label_path = os.path.join(self.root_dir, self.label_dir)
        self.image_path = os.path.join(self.root_dir, self.image_dir)
        self.image_list = os.listdir(self.image_path)
        self.label_list = os.listdir(self.label_path)
        self.transform = transform
        # 因为label 和 Image文件名相同，进行一样的排序，可以保证取出的数据和label是一一对应的
        self.image_list.sort()
        self.label_list.sort()

    def __getitem__(self, idx):
        img_name = self.image_list[idx]
        label_name = self.label_list[idx]
        img_item_path = os.path.join(self.root_dir, self.image_dir, img_name)
        label_item_path = os.path.join(self.root_dir, self.label_dir, label_name)
        img = Image.open(img_item_path)

        with open(label_item_path, 'r') as f:
            label = f.readline()

        # img = np.array(img)
        img = self.transform(img)
        sample = {'img': img, 'label': label}
        return sample

    def __len__(self):
        assert len(self.image_list) == len(self.label_list)
        return len(self.image_list)

if __name__ == '__main__':
    transform = transforms.Compose([transforms.Resize((256, 256)), transforms.ToTensor()])
    root_dir = "dataset/train"
    image_ants = "ants_image"
    label_ants = "ants_label"
    ants_dataset = MyData(root_dir, image_ants, label_ants, transform)
    image_bees = "bees_image"
    label_bees = "bees_label"
    bees_dataset = MyData(root_dir, image_bees, label_bees, transform)
    train_dataset = ants_dataset + bees_dataset

    # transforms = transforms.Compose([transforms.Resize(256, 256)])
    dataloader = DataLoader(train_dataset, batch_size=1, num_workers=2)

    writer.add_image('error', train_dataset[119]['img'])
    writer.close()
    # for i, j in enumerate(dataloader):
    #     # imgs, labels = j
    #     print(type(j))
    #     print(i, j['img'].shape)
    #     # writer.add_image("train_data_b2", make_grid(j['img']), i)
    #
    # writer.close()

五、TensorBorad的使用

安装tensorborad:pip install tensorboard

更改端口：

六、Transformer

进入structure

1.compose

将几个步骤合为一个

2.toTensor

将PIL和numpy类型的图片转为Tensor（可用于训练）

__call__的使用：
ctrl+p提示函数参数

3.Normalize

讲一个tensor类型进行归一化

4.Resize

tips:

七、torchvision中数据集的使用

torchvision 是PyTorch中专门用来处理图像的库。这个包中有四个大类。

torchvision.datasets

torchvision.models

torchvision.transforms

torchvision.utils

这里主要介绍前三个。

1.torchvision.datasets

八、dataloader

drop_last=true,舍去最后的余数图片，如上半张图片将会舍去，下半张图片为FALSE

九、nn.module

十、卷积操作

十一、卷积层

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
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.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()

writer = SummaryWriter("../logs")

step = 0
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    print(imgs.shape)
    print(output.shape)
    # torch.Size([64, 3, 32, 32])
    writer.add_images("input", imgs, step)
    # torch.Size([64, 6, 30, 30])  -> [xxx, 3, 30, 30]

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

    step = step + 1

十二、池化层

import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

dataloader = DataLoader(dataset, batch_size=64)

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

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

tudui = Tudui()

writer = SummaryWriter("../logs_maxpool")
step = 0

for data in dataloader:
    imgs, targets = data
    writer.add_images("input", imgs, step)
    output = tudui(imgs)
    writer.add_images("output", output, step)
    step = step + 1

writer.close()

十三、非线性激活

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

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

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

dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.relu1 = ReLU()
        self.sigmoid1 = Sigmoid()

    def forward(self, input):
        output = self.sigmoid1(input)
        return output

tudui = Tudui()

writer = SummaryWriter("../logs_relu")
step = 0
for data in dataloader:
    imgs, targets = data
    writer.add_images("input", imgs, global_step=step)
    output = tudui(imgs)
    writer.add_images("output", output, step)
    step += 1

writer.close()

十四、线性层

import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader

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.linear1 = Linear(196608, 10)

    def forward(self, input):
        output = self.linear1(input)
        return output

tudui = Tudui()

for data in dataloader:
    imgs, targets = data
    print(imgs.shape)
    output = torch.flatten(imgs)
    print(output.shape)
    output = tudui(output)
    print(output.shape)

十五、Sequential

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()

十六、损失函数和反向传播

1.损失函数

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

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

dataloader = DataLoader(dataset, batch_size=1)

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)
    result_loss = loss(outputs, targets)
    print("ok")

2.反向传播及优化

import torch
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.optim.lr_scheduler import StepLR
from torch.utils.data import DataLoader

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

dataloader = DataLoader(dataset, batch_size=1)

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)
scheduler = StepLR(optim, step_size=5, gamma=0.1)
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()
        result_loss.backward()
        scheduler.step()
        running_loss = running_loss + result_loss
    print(running_loss)

十七、现有模型的使用及修改

import torchvision

# train_data = torchvision.datasets.ImageNet("../data_image_net", split='train', download=True,
#                                            transform=torchvision.transforms.ToTensor())
from torch import nn

vgg16_false = 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))
print(vgg16_true)

print(vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096, 10)
print(vgg16_false)

十八、网络模型的保存和修改

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）
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
from model_save import *
# 方式1-》保存方式1，加载模型
import torchvision
from torch import nn

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"))
# model = torch.load("vgg16_method2.pth")
# print(vgg16)

# 陷阱1
# 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)

只用方式2！！！！

十九、完整的模型训练套路

import torchvision
from my_model import  *
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
tudui = Tudui()

#损失函数
loss_fn = nn.CrossEntropyLoss()

#优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

#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 += 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 += loss
            accuracy = (outputs.argmax(1)==targets).sum()
            total_accuracy += accuracy
    print("整体集上的Loss:{}".format(total_test_loss))
    print("整体数据集上的正确率：{}".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 += 1

    torch.save(tudui,"tudui_{}.pth".format(i))
    #torch.save(tudui.state_dict(),"tudui_{}".format(i))
    print("模型已保存")

writer.close()

二十、利用GPU训练

import torchvision
from torch.utils.tensorboard import SummaryWriter
import torch
import time

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


device = torch.device("cuda")
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.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
tudui = Tudui()
tudui=tudui.to(device)

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

#优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

#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")

start_time=time.time()
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 += 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time-start_time)
            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 += loss
            accuracy = (outputs.argmax(1)==targets).sum()
            total_accuracy += accuracy
    print("整体集上的Loss:{}".format(total_test_loss))
    print("整体数据集上的正确率：{}".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 += 1

    torch.save(tudui,"tudui_{}.pth".format(i))
    #torch.save(tudui.state_dict(),"tudui_{}".format(i))
    print("模型已保存")

writer.close()

二十一、完整的模型验证套路

# -*- coding: utf-8 -*-
# 作者：小土堆
# 公众号：土堆碎念
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')    # 因为png格式是四通道，除了RGB三通道外，还有一个透明度通道，
# 调用convert保留其颜色通道。当然，如果图片本来就是三个颜色通道，经此操作，不变。加上这一步可以适应png jpg各种格式的图片
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))

---

总结

。