pytorch以及神经网络基础

---

• 使用help时，里面的小括号要去掉

• 在pycharm中打开文件夹
  
• 在anaconda中激活pytorch：conda activate pytorch

TensorBoard 的使用

• 画一幅图像

from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter('logs')

for i in range(100):
    writer.add_scalar('y = 3x', 3 * i, i)

writer.close()

运行程序，然后在terminal中，激活pytorch，再输入tensorboard --logdir=logs --port=6007

H：高度，W：宽度，C:通道

• 显示数据集的图像

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

writer = SummaryWriter("logs")
image_path = "data/train/ants_image/6240329_72c01e663e.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

writer.add_image("train", img_array, 1, dataformats='HWC')
# y = 2x
for i in range(100):
    writer.add_scalar("y=2x", 3*i, i)

writer.close()

Transfrom的使用

• 看源代码：按住ctrl，鼠标左键点函数名
• 找快捷键：file->setting->输入keymap->输入想查找的快捷键如：“structure”

ToTensor和Normalize的使用

• 16行中两个参数分别是三通道的“均值”和“方差”
  

• 不勾选的话就是忽略大小写，输入r也能自动补全Resize
  

• resize和compose的使用

• resize参数可以是（h，w）高度和宽度

• 也是int，等比例缩放
  

• randomcrop随机裁剪
  

• 不知道什么数据类型

  • print
  • print（type）
  • 断点调试

torchvision数据集的使用

• CIFAR10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("p10")
# for i in range(10):
#     img, target = test_set[i]
#     writer.add_image("test_set", img, i)
#
# writer.close()

dataloader的使用

• dataset，数据集名字
• batch_size每次调用数据集里几张照片
• shuffle每次调用完是否打乱剩下的，true代表打乱，一般为true
• num_workers，进程数，为0的话就是只有主进程工作，windows一般为0，因为大于0是可能报错
• drop_last，假如100张图片，每次3张，调用99张之后还剩1张，如果设置成true，则舍去剩下那一张
  

import torchvision

# 准备的测试数据集
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

# 每次取64个图，每行8个，形成一个大图
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("dataloader")
for epoch in range(2):  # 两轮画图
    step = 0
    for data in test_loader: # test_loader的大小为：数据集的大小/64，在这里为10000/64=155
        imgs, targets = data
        # print(imgs.shape)
        # print(targets)
        writer.add_images("Epoch: {}".format(epoch), imgs, step)
        step = step + 1

writer.close()

nn.Module的使用

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

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)

卷积

Conv2d

• input：输入的数据
• weight：卷积核
• stride：每次卷积核移动的位数，默认为1
• padding：上下左右是否扩充，值为1时，上下左右扩充1，扩充的值为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)

卷积层

• 常用前5个参数，分别是输入通道数，输出通道数，卷积核大小，移动步长，是否补充，其他的参数用的比较少

• 卷积核大小可以为一个常数也可以为一个元组
  
• 根据公式可以计算输出图像的高和宽
  

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

池化层

• 最大池化也叫下采样
• 池化核大小（和卷积层类似），步长（默认不是1，是池化核的大小），是否补充，池化核相邻两个像素点距离为多少
  
• ceil_mode：当池化核和图像交集不足池化核的大小时是否保留，等于True就是保留（默认值为False）
  

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()

• 池化层作用：在保留图片特征的同时减小数据量

非线性激活

• 作用，对像素点小于0的部分进行截断，即像素值大于等于0
• inplace:等于True即直接替换
  

import torch
import torchvision
from torch import nn
from torch.nn import ReLU, Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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()

线性层

torch.nn.Linear(in_features, out_features, bias=True, device=None, dtype=None)

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)

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()

损失函数和反向传播

• Loss Function：计算是实际输出和目标之间的差距，为我们更新输出提供一定的依据
• 损失函数类型：全部求和型，求和去平均，平方和取平均，交叉熵

import torch
from torch.nn import L1Loss
from torch import nn

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')
result = loss(inputs, targets)

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

print(result)
print(result_mse)


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)

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")

优化器

• TORCH.OPTIM

• Adam优化器
• torch.optim.Adam(params, lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0, amsgrad=False, *, foreach=None, maximize=False, capturable=False, differentiable=False, fused=False)
• 第一个参数：模型的参数，第二个：模型的学习率，剩余的是特定优化器的参数
• 

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)

修改现有网络

网络模型的保存和读取

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")

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))

完整的训练套路

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)

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

writer.close()

• tensor：一个可以运行在GPU上的多维数据
• argmax：返回最大值所在的位置

使用GPU加速

• 模型，数据，损失函数可以使用cuda加速
• 
  

完整的验证套路

• PNG格式的图片有四个通道，除了三个颜色通道还有一个透明度通道，使用png格式的图片时，要加image = image.convert('RGB')，来保留其颜色通道，如果原来就是三通道，加上这步不会改变结果。

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))