model.py 搭建神经网络架构

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))    # 构造一个输入数据
    output = tudui(input)                
    print(output.shape)                    # 测试模型的输出是否符合预期

train.py 模型训练

GPU 训练需要修改三个部分：

1. 网络模型
2. 数据（输入、标签）
3. 损失函数

GPU 训练有两种修改方式：

1. **.cuda()**
2. device = torch.device("cuda" if torch.cuda.is_available() else "cpu")，**.to(device)** ```python import torch 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

定义训练的设备

device = torch.device(“cuda” if torch.cuda.is_available() else “cpu”)

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(6444, 64), nn.Linear(64, 10) )

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

tudui = Tudui() tudui = tudui.to(device) # 1. 将网络模型结构送入 GPU

损失函数

loss_fn = nn.CrossEntropyLoss() loss_fn = loss_fn.to(device) # 3. 将损失函数送入 GPU

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
    imgs = imgs.to(device)
    targets = targets.to(device)        # 2. 将数据（输入和标签）送入 GPU
    outputs = tudui(imgs)
    loss = loss_fn(outputs, targets)
    # 优化器优化模型
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    total_train_step = total_train_step + 1
    if total_train_step % 100 == 0:
        print("训练次数：{}, Loss: {}".format(total_train_step, loss.item()))
        writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
    for data in test_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)    # 2. 将数据（输入和标签）送入 GPU
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)
        total_test_loss = total_test_loss + loss.item()
        accuracy = (outputs.argmax(1) == targets).sum()
        total_accuracy = total_accuracy + accuracy
print("整体测试集上的Loss: {}".format(total_test_loss))
print("整体测试集上的正确率: {}".format(total_accuracy/test_data_size))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")

writer.close()

<a name="WLLbt"></a>
# test.py 模型测试/推理
```python
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))
# 注意 eval 和 no_grad
model.eval()
with torch.no_grad():
    output = model(image)
print(output)
print(output.argmax(1))