（3）完整模型的训练与验证

整体步骤：

　　准备数据集--》利用dataloader来加载数据集--》创建网络模型--》创建损失函数、优化器--》设置训练网络的一些参数（训练的次数、测试的次数、epoch）--》添加tensorboard--》每次训练（每个epoch）下：训练集上：分割数据，loss，清零，优化；测试集上：分割数据，计算准确度--》得到loss、accuracy

model.py

#搭建神经网络
import torch
from torch import nn

class Qian(nn.Module):
    def __init__(self):
        super(Qian, self).__init__()
        self.model1 = nn.Sequential(
            nn.Conv2d(3, 32, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(1024, 64),
            nn.Linear(64, 10)
        )

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

if __name__ == '__main__':
    qian = Qian()
    input = torch.ones((64, 3, 32, 32))
    output = qian(input)
    print(output.shape)

train.py

import torchvision
from torch.utils.tensorboard import SummaryWriter
import time
from model import *
#准备数据集
from torch import nn
from torch.utils.data import DataLoader

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
train_data = torchvision.datasets.CIFAR10(root="./datasets", train=True, transform=dataset_transform, download=True)
test_data = torchvision.datasets.CIFAR10(root="./datasets", train=False, transform=dataset_transform, download=True)

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
qian = Qian()

#创建损失函数
loss_fn = nn.CrossEntropyLoss()

#优化器
learning_rate = 0.01#1e-2=1x10^(-2)
optimizer = torch.optim.SGD(qian.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("log_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
    qian.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = qian(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
    qian.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = qian(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(qian, "qian_{}.pth".format(i))
    print("模型已保存")
    #torch.save(qian.state_dict(), "qian_{}.pth".format(i))
writer.close()

test.py

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

image_path = "imgs/dog.png"
image = Image.open(image_path)
image = image.convert('RGB')

print(image)
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
                                            torchvision.transforms.ToTensor()])
image = transform(image)
print(image.shape)
class Qian(nn.Module):
    def __init__(self):
        super(Qian, self).__init__()
        self.model1 = nn.Sequential(
            nn.Conv2d(3, 32, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, (5, 5), (1, 1), padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(1024, 64),
            nn.Linear(64, 10)
        )

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

model = torch.load("qian_0.pth")
print(model)
# output = model(image)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
     output = model(image)
print(output)
print(output.argmax(1))

 若使用gpu训练，则需要在以下部分加.cuda()

qian = Qian()
if torch.cuda.is_available():
    qian = qian.cuda()


loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()