Pytorch入门

本文最后更新于：2024年10月22日 下午

PyTorch入门

来源于bilibili土堆视频笔记

加载数据

Dataset类

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
#read_data.py
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)


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)

train_dataset = ants_dataset + bees_dataset

Tensorboard的使用

1
tensorboard --logdir=logs --port=6007

image-20240610122550969

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image

writer = SummaryWriter("logs")
image_path = "data/train/bees_image/16838648_415acd9e3f.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

writer.add_image("test", img_array, 2, dataformats='HWC')

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

writer.close()

Transformes

image-20240610212315403

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

# tensor数据类型
# 通过transforms.ToTensor解决两个问题
# 1.transforms如何使用
# 2.tensor数据

img_path = "data/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()

image-20240620210452723

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

writer = SummaryWriter("logs")
img = Image.open("images/5650366_e22b7e1065.jpg")
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([6, 3, 2], [9, 3, 5])
img_norm = trans_norm(img_tensor)
# print(img_norm[0][0][0])
writer.add_image("Normalize",img_norm,2)

# Resize
print(img.size)
trans_resize = transforms.Resize((256, 256))
# img PIL -> resize -> img_resize PIL
img_resize = trans_resize(img)
print(type(img_resize))

# img_resize PIL -> totensor -> img_resize tensor
img_resize = trans_totensor(img_resize)
writer.add_image("Resize",img_resize,0)


# Compose - resize - 2
trans_resize_2 = transforms.Resize(256)
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Compose",img_resize_2,1)

# RandomCrop
trans_random = transforms.RandomCrop(256)
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()

torchvision中数据集的使用

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset1", train=False, 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()

writer = SummaryWriter("p14")
for i in range(10):
    img, target = test_set[i]
    writer.add_image("test_set", img, i)

writer.close()

DataLoader

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
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("./dataset1",
                                         train=False,
                                         transform=torchvision.transforms.ToTensor(),
                                         )

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

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

writer = SummaryWriter("dataloader")

for epoch in range(2):
    step = 0
    for data in test_loader:
        imgs, targets = data
        writer.add_images(f"Epoch{epoch}", imgs, step)
        step = step + 1

writer.close()

神经网络的基本骨架-nn.Module

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
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, 0]])

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

output = F.conv2d(input, kernel, stride=2)
print(output)
# padding
output = F.conv2d(input, kernel, stride=1, padding=1)
print(output)

卷积层

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
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("./dataset1",
                                       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):
        return self.conv1(x)


tudui = Tudui()

writer = SummaryWriter("dataloader")
step = 0
for data in dataloader:
    imgs, target = 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()

最大池化的使用

image-20240712111134822

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
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("./dataset1",
                                       train=False,
                                       download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)

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

非线性激活

image-20240712113254623

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
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]])

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

dataset = torchvision.datasets.CIFAR10("./dataset1",
                                       train=False,
                                       download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)


class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__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, global_step=step)
    step = step + 1

writer.close()

线性层和其他层

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader
import torch

dataset = torchvision.datasets.CIFAR10("./dataset1",
                                       train=False,
                                       download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)

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

神经网络搭建实战和Sequential

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
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()

损失函数与反向传播

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("./dataset1",
                                       train=False,
                                       download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1)


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(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(result_loss)
    result_loss.backward()
    print('ok')

优化器

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
import torch.optim
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("./dataset1",
                                       train=False,
                                       download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1)


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(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)
        result_loss = loss(outputs, targets)
        optim.zero_grad()
        result_loss.backward()
        optim.step()
        running_loss = running_loss + result_loss
    print(running_loss)

现有网络模型的使用和修改

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
import torchvision
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("./dataset1",
                                          train=True,
                                          download=True,
                                          transform=torchvision.transforms.ToTensor())
vgg16_true.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)

模型的保存和加载

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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, "models/vgg16_method1.pth")

# 保存方式2 模型参数（官方推荐）
torch.save(vgg16.state_dict(), "models/vgg16_method2.pth")

# 陷阱
class Tudui(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=5)

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


tudui = Tudui()
torch.save(tudui, "models/tudui_method1.pth")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import torch
import torchvision
from model_save import *

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

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

# 陷阱1
model = torch.load("models/tudui_method1.pth")
print(model)

完整模型训练套路

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
# 搭建神经网络
import torch
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, 1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            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)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter

from model import *
from torch.utils.data import DataLoader

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                         train=False,
                                         transform=torchvision.transforms.ToTensor(),
                                         download=True)
# 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))

# 利用DataLoader加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
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)

# 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)

        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 += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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 += 1

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

writer.close()

使用GPU训练

方法1： .cuda

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
import torch
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter
import time
from torch.utils.data import DataLoader

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                         train=False,
                                         transform=torchvision.transforms.ToTensor(),
                                         download=True)
# 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))

# 利用DataLoader加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, 1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

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


tudui = Tudui()
tudui = tudui.cuda()

# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.cuda()

# 优化器
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 = 20

# 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.cuda()
        targets = targets.cuda()
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

        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.cuda()
            targets = targets.cuda()
            outputs = tudui(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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 += 1

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

writer.close()

方法2 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
import torch
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter
import time
from torch.utils.data import DataLoader

# 定义设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                          train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset1",
                                         train=False,
                                         transform=torchvision.transforms.ToTensor(),
                                         download=True)
# 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))

# 利用DataLoader加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, 1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            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)

# 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 = 20

# 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)

        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 += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            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 += 1

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

writer.close()

测试

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
import torch
import torchvision
from PIL import Image
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear

# 使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

img_path = "./imgs/img.png"
image = Image.open(img_path)
print(image)

transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
                                            torchvision.transforms.ToTensor()])
image = transform(image)
print(image.shape)

# 创建网络模型
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, 1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, 1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

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


model = torch.load("models/tudui_19.pth", map_location=torch.device('cpu'))
image = torch.reshape(image, (1, 3, 32, 32))

model.eval()
with torch.no_grad():
    output = model(image)
print(output)

print(output.argmax(1))

AI
#Pytorch #深度学习
Pytorch入门
https://furthur509.github.io/2024/10/22/PyTorch入门/
作者
Yang Mingxin
发布于
2024年10月22日
许可协议