pytorch学习笔记（7)（入门完结）

    经过一段时间的学习，终于初步入门了pytorch，经过这么长时间的学习，收获了很多，我们一定要记住，天道酬勤，学习一定要坚持不懈，终身学习，养成学习的兴趣！加油，我们都能在生活中找到自己的目标！今天是学习笔记入门的最后一篇，主要写了将神经网络模型送入gpu进行运算的代码，同时也写了验证的代码，大家一起加油!

import torch.optim
import torchvision
import time


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

#准备训练设备
device = torch.device("cuda")

train_data = torchvision.datasets.CIFAR10(root="dataset",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="dataset",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)

#创建神经网络
class B(nn.Module):
    def __init__(self):
        super(B, 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
b = B()
b = b.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(b.parameters(),lr=learning_rate)

#设置训练网络的一些参数
#记录模型参数
i=0
#记录测试的次数
total_test_step =0
#记录训练的次数
total_train_step = 0
#训练的轮数
epoch = 20

#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
    b.train()
    for data in train_dataloader:
        imgs,targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        output = b(imgs)
        loss = loss_fn(output,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
    b.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 = b(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(b,"tudui_{}.pth".format(i))
    print("模型保存成功")
    i=i+1

    下面是验证的代码：

import torch
import torchvision
from PIL import  Image
from torch import nn
image = Image.open("imgs/bird2.jpg")

transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize((32,32)),
    torchvision.transforms.ToTensor()
])
image = transform(image)
class B(nn.Module):
    def __init__(self):
        super(B, 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_19.pth",map_location='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))