注：参考B站‘小土堆’视频教程

视频链接：【PyTorch深度学习快速入门教程（绝对通俗易懂！）【小土堆】

系列文章：
深度学习快速入门----Pytorch 系列1
深度学习快速入门----Pytorch 系列2
深度学习快速入门----Pytorch 系列3

文章目录

• • 一、完整的模型训练套路
  • • • 1、预备知识
      • 2、步骤
      • 3、代码
      • 4、运行结果
  • 二、利用GPU训练
  • • • 1、需要修改的地方
      • 2、比较CPU与GPU训练耗费时间
      • 3、用.to(device)的方式
  • 三、完整的模型验证套路

一、完整的模型训练套路

1、预备知识

通过argmax计算正确率：

import torchoutputs = torch.tensor([[0.1,0.2],[0.3,0.4]])print(outputs.argmax(1))
preds = outputs.argmax(1)
targets = torch.tensor([0,1])
print((preds == targets).sum())

思路

2、步骤

• 准备数据集
• 利用 DataLoader 来加载数据集
• 创建网络模型
• 损失函数
• 优化器
• 设置训练网络的一些参数
• 设置训练轮数

  • 训练步骤

    • 计算损失函数
    • 优化

  • 测试步骤

    • 计算损失函数
    • 计算准确率
• 展示
• 保存模型

3、代码

# model.py
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 xif __name__ == '__main__':tudui = Tudui()input = torch.ones((64, 3, 32, 32))output = tudui(input)print(output.shape)

# train.py
import torchvision
from torch.utils.tensorboard import SummaryWriterfrom model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoadertrain_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)# 创建网络模型
tudui = Tudui()# 损失函数
loss_fn = nn.CrossEntropyLoss()# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
# 随机梯度下降法
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 = dataoutputs = 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 + 1if 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# 整体正确率total_accuracy = 0with torch.no_grad():for data in test_dataloader:imgs, targets = dataoutputs = 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 + accuracyprint("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# 保存某一轮训练后的结果torch.save(tudui, "tudui_{}.pth".format(i))print("模型已保存")writer.close()

4、运行结果

tensorboard:

二、利用GPU训练

1、需要修改的地方

• 网络模型
• 数据（输入，标注）
• 损失函数
• .cuda()

import torch
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 DataLoadertrain_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(64*4*4, 64),nn.Linear(64, 10))def forward(self, x):x = self.model(x)return x
tudui = Tudui()
if torch.cuda.is_available():tudui = tudui.cuda()# 损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():loss_fn = loss_fn.cuda()
# 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")
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 = dataif torch.cuda.is_available():imgs = imgs.cuda()targets = targets.cuda()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 + 1if 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 = 0total_accuracy = 0with torch.no_grad():for data in test_dataloader:imgs, targets = dataif torch.cuda.is_available():imgs = imgs.cuda()targets = targets.cuda()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 + accuracyprint("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 + 1torch.save(tudui, "tudui_{}.pth".format(i))print("模型已保存")writer.close()

2、比较CPU与GPU训练耗费时间

• CPU
  
• GPU
  

3、用.to(device)的方式

# ···# 定义训练的设备
device = torch.device("cuda")# ···tudui = Tudui()
tudui = tudui.to(device)# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)# ···# 训练步骤开始tudui.train()for data in train_dataloader:imgs, targets = dataimgs = imgs.to(device)targets = targets.to(device)outputs = tudui(imgs)loss = loss_fn(outputs, targets)# ···# 测试步骤开始tudui.eval()total_test_loss = 0total_accuracy = 0with torch.no_grad():for data in test_dataloader:imgs, targets = dataimgs = 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

三、完整的模型验证套路

用GPU训练30轮后的网络模型：

import torch
import torchvision
from PIL import Image
from torch import nnimage_path = "imgs/dog.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 xmodel = torch.load("tudui_29_gpu.pth", map_location=torch.device('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))

运行结果：

与CIFAR10数据集比较，预测正确：