pytorch基本操作 pytorch 快速入门

目录

• Dataset类代码实战
• TensorBoard的使用
• Transforms的使用
• 常见的Transforms
• torchvision中数据集的使用
• Dataloader的使用
• 神经网络的基本骨架nn.module
• 卷积操作
• 卷积层
• 池化层
• 非线性激活层
• 线性层
• Sequential
• 损失函数与反向传播
• 优化器
• 现有网络模型的使用及修改
• 网络模型的保存与读取
• 完整的模型训练套路
• 利用GPU训练
• 完整的模型验证套路

本文参考：https://www.bilibili.com/video/BV1hE411t7RN

Dataset类代码实战

数据集地址：https://download.pytorch.org/tutorial/hymenoptera_data.zip

数据集压缩包为45M，包括两类图片：bees 和 ants
在 hymenoptera_data\train\ants 中，存在 imageNotFound.gif，有些特殊。在准备数据时，需要判断是否要做删除处理

数据集载入

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(self.root_dir, self.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)


if __name__ == '__main__':

    root = r"D:\PycharmProjects\learn-pytorch\dataset\train"
    # root = r"dataset\train"
    ants_label_dir = "ants"
    bees_label_dir = "bees"
    ants_dataset = MyData(root, ants_label_dir)
    bees_dataset = MyData(root, bees_label_dir)
    train_dataset = ants_dataset + bees_dataset

生成txt标签文件

import os

root_dir = "dataset/train"
target_dir = ["ants_image", "bees_image"]
out_dir = ["ants_label", "bees_label"]
for i in range(0, 2):
    img_path = os.listdir(os.path.join(root_dir, target_dir[i]))
    label = target_dir[i].split('_')[0]
    for j in img_path:
        file_name = j.split('.jpg')[0]
        if not os.path.exists(os.path.join(root_dir, out_dir[i])):
            os.mkdir(os.path.join(root_dir, out_dir[i]))
        with open(os.path.join(root_dir, out_dir[i], "{}.txt".format(file_name)), 'w') as f:
            f.write(label)

TensorBoard的使用

pip安装指令

pip install tensorboard

启动tensorboard

tensorboard --logdir=<directory_name>

在PyCharm终端中输入指令

测试代码

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

writer = SummaryWriter("logs")
img_path = "dataset/train/ants_image/0013035.jpg"
img_PIL = Image.open(img_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

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

writer.close()

注：若显示出问题，则logs中文件可以删除，重新运行

Transforms的使用

1. transforms如何使用

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

img_path = "dataset/train/ants_image/0013035.jpg"
img = Image.open(img_path)

writer = SummaryWriter("logs")
tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)

writer.add_image("Tensor_img", tensor_img)

writer.close()

2. 为什么需要tensor数据类型

神经网络需要的输入数据格式

常见的Transforms

关注输入输出类型
多看官方文档

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

writer = SummaryWriter("logs")
img_path = "images/pytorch.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([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize", img_norm)

# Resize
print(img.size)
trans_resize = transforms.Resize((512, 512))
# img PIL -> resize -> img_resize PIL
img_resize = trans_resize(img)
# img_resize PIL -> ToTensor -> img_resize tensor
img_resize = trans_totensor(img_resize)
writer.add_image("Resize", img_resize)
print(img_resize.size)

# 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("img_resize_2", img_resize_2)

# RandomCrop
tran_random = transforms.RandomCrop((500, 1000))
trans_compose_2 = transforms.Compose([tran_random, trans_totensor])
for i in range(10):
    img_random = trans_compose_2(img)
    writer.add_image("img_random", img_random, i)

writer.close()

torchvision中数据集的使用

cifar10数据集：https://www.cs.toronto.edu/~kriz/cifar.html

CIFAR-10 数据集由 10 个类别的 60000 个 32x32 彩色图像组成，每个类别包含 6000 个图像。 有50000张训练图像和10000张测试图像。数据集分为五个训练批次和一个测试批次，每个批次有 10000 张图像。 测试批次恰好包含来自每个类别的 1000 个随机选择的图像。 训练批次包含随机顺序的剩余图像，但一些训练批次可能包含来自一个类的图像多于另一个。 在它们之间，训练批次正好包含来自每个类别的 5000 张图像。存档包含文件 data_batch_1、data_batch_2、…、data_batch_5 以及 test_batch。 这些文件中的每一个都是使用 cPickle 生成的 Python“腌制”对象。 这是一个 python3 例程，它将打开这样一个文件并返回一个字典：

def unpickle(file):
    import pickle
    with open(file, 'rb') as fo:
        dict = pickle.load(fo, encoding='bytes')
    return dict

以这种方式加载，每个批处理文件都包含一个包含以下元素的字典：

• data $\to$
• label $\to$

数据集包含另一个文件，称为 batches.meta。 它也包含一个 Python 字典对象。 它具有以下条目：

• label_names $\to$

测试代码

import torchvision
from torch.utils.tensorboard import SummaryWriter

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

train_set = torchvision.datasets.CIFAR10(root="./dataset-cifar10", train=True, transform=dataset_transform, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset-cifar10", 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(img)

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()

显示结果

Dataloader的使用

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

test_set = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)

test_loader = DataLoader(dataset=test_set, batch_size=64, shuffle=True, num_workers=0, drop_last=True)

img, target = test_set[0]
print(img.shape)
print(target)

writer = SummaryWriter("logs")
for epoch in range(2):
    step = 0
    for data in test_loader:
        imgs, targets = data
        # print(imgs.shape)
        # print(targets)
        writer.add_images("epoch: {}".format(epoch), imgs, step)
        step += 1

由于shuffle=True，两次epoch抓取顺序不一样

神经网络的基本骨架nn.module

官网例子

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

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__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))

重写方法就行

import torch
from torch import nn


class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()

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


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

卷积操作

测试代码

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]])

print(input)
print(kernel)

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

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

output_2 = F.conv2d(input, kernel, stride=2)
print(output_2)
print(output_2.shape)

output_3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output_3)
print(output_3.shape)

卷积层

测试代码

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(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=64)


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


writer = SummaryWriter("logs")
tudui = Tudui()
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("imgs", 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 += 1

经过一个卷积层后的结果

池化层

测试代码

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(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=64)

# 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().__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)

    def forward(self, x):
        x = self.maxpool1(x)
        return x


writer = SummaryWriter("logs")
tudui = Tudui()
# output = tudui(input)
# print(output)
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("imgs", imgs, step)
    # torch.Size([64, 3, 10, 10])
    writer.add_images("output", output, step)
    step += 1

最大池化作用效果

非线性激活层

经过sigmoid层后

测试代码

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(root="dataset-cifar10", 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.relu1 = ReLU()
        self.sigmoid1 = Sigmoid()

    def forward(self, x):
        y = self.sigmoid1(x)
        return y


tudui = Tudui()
# output = tudui(input)
# print(output)
writer = SummaryWriter("logs")
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()

尝试一下BN层

线性层

打平函数torch.flatten

测试代码

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

dataset = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)

dataloader = DataLoader(dataset, batch_size=64, drop_last=True)


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.reshape(imgs, (1, 1, 1, -1))
    output = torch.flatten(imgs)
    print(output.shape)
    output = tudui(output)
    print(output.shape)

Sequential

搭建模型

测试代码

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


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

        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(64 * 4 * 4, 64),
            Linear(64, 10),
            Softmax(dim=1)
        )

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


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

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

使用tensorborad中的add_graph方法显示模型图

损失函数与反向传播

绝对误差

均方误差

交叉熵

测试代码

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

loss = L1Loss()
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)

'''
输出结果：
tensor(0.6667)
tensor(1.3333)
tensor(1.1019)
'''

网络中使用损失函数

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

dataset = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)

dataloader = DataLoader(dataset, batch_size=1, drop_last=True)


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

        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(64 * 4 * 4, 64),
            Linear(64, 10),
            # Softmax(dim=1)
        )

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


loss = nn.CrossEntropyLoss()
tudui = Tudui()
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    # print(output)
    # print(targets)
    result_loss = loss(output, targets)
    # print(result_loss)
    result_loss.backward()
    print("ok!")

优化器

测试代码

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

dataset = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=False, transform=torchvision.transforms.ToTensor(), download=True)

dataloader = DataLoader(dataset, batch_size=1, drop_last=True)


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

        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(64 * 4 * 4, 64),
            Linear(64, 10),
            # Softmax(dim=1)
        )

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


loss = nn.CrossEntropyLoss()
tudui = Tudui()
optimizer = torch.optim.SGD(tudui.parameters(), lr=0.01)
for epoch in range(20):
    running_loss = 0.0
    for data in dataloader:
        imgs, targets = data
        output = tudui(imgs)
        result_loss = loss(output, targets)
        optimizer.zero_grad()
        result_loss.backward()
        optimizer.step()
        # print(result_loss)
        running_loss += result_loss
    print(running_loss)

现有网络模型的使用及修改

经典图像分类数据集ImageNet

测试代码

import torchvision
from torch import nn

# train_data = torchvision.datasets.ImageNet("data_imageNet", 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("dataset-cifar10", 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)

生成预训练模型

Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to C:\Users\SJN/.cache\torch\checkpoints\vgg16-397923af.pth
100.0%

VGG16原始模型

VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace=True)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace=True)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace=True)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace=True)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace=True)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace=True)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace=True)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace=True)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace=True)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace=True)
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

网络模型的保存与读取

模型保存

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")

模型读取

import torch
import torchvision
from torch import nn
from P26_modelSave import *

# 加载方式1 -> 保存方式1
model = torch.load("vgg16_method1.pth")
print(model)

# 加载方式2 -> 保存方式2
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
# 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)

完整的模型训练套路

待搭建的模型

模型搭建代码

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)

完整训练代码

import torchvision
from torch.utils.tensorboard import SummaryWriter
from P27_model import *
from torch.utils.data import DataLoader


# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=True, transform=torchvision.transforms.ToTensor(), download=True)

test_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", 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")

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().item()  # 正确率
            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))

writer.close()

注意：加item()

利用GPU训练

方式一：对模型，损失函数，数据三种对象调用cuda()

import torch
import torchvision
from torch import nn
from torch.utils.tensorboard import SummaryWriter
# from P27_model import *
from torch.utils.data import DataLoader


# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=True, transform=torchvision.transforms.ToTensor(), download=True)

test_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", 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()
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
# 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")

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().item()  # 正确率
            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))

writer.close()

方式二：使用Google Colab加速

方式三：使用to(device)

import torch
import torchvision
from torch import nn
from torch.utils.tensorboard import SummaryWriter
# from P27_model import *
from torch.utils.data import DataLoader
import time

# 定义训练的设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", train=True, transform=torchvision.transforms.ToTensor(), download=True)

test_data = torchvision.datasets.CIFAR10(root="dataset-cifar10", 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.to(device)

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

# 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")
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 = 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 = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum().item()  # 正确率
            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))

writer.close()

完整的模型验证套路

预测类别

测试代码

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

image_path = "./images/dog.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))

'''
预测结果：
tensor([[-8.4646, -4.6589,  2.4350,  3.5231, -2.1238, 14.2050, -3.9244,  6.7765,
         -8.8615, -1.1546]])
tensor([5])
'''