Pytorch学习笔记（3）多分类网络的总体搭建和调用gru训练

   话不多说我们直接先把完整的代码贴出来

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")

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 Net(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
net = Net()
net = net.to(device)

# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = 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(net.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 = 100

# 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)
        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)
            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
    if i%10==0:
        torch.save(tudui, "tudui_{}.pth".format(i))
    print("模型已保存")

writer.close()

  接下来我对整体的过程做一个总结：

1.训练集和测试集的导入

2.神经网络模型的搭建和实例化

3.训练集进行参数调优

    3.1.输入->输出

    3.2.计算损失值

    3.3.计算梯度

    3.4.反向传播更新梯度

4.测试集进行测试

我接着记录几点容易遗忘的知识点

1.优化器的调用

optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate)

  我们在初始化优化器的时候需要传入两个参数,第一个是神经网络的参数,如weight啊bias啊,因为优化的就是这些东西,第二个是学习速率,也就是learning rate

2.如何使用gpu进行模型的训练

  相比于上文中的代码所使用的,我更倾向于以下方法调用gpu

device=torch.device("cuda:0" if torch.cuda.is_avaliable() else "cpu")

  接着对实例化网络,输入的图片,输入的标签,优化器,损失函数都转为gpu,就可以进行gpu进行网络训练了.

3.colab

谷歌里的colab可以进行gpu训练,他提供的显卡是16显存的特斯拉T4显卡,相当牛掰,只要有个谷歌账号每周就可以使用30个小时