PyTorch深度学习快速入门（b站小土堆）P27-笔记

PyTorch深度学习快速入门（b站小土堆）P16-26 笔记

完整的模型训练套路

 文件名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,padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(1024,64),
            nn.Linear(64,10)
        )

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

#1验证该模型
if __name__ == '__main__':
    tudui = Tudui()
    input = torch.ones((64,3,32,32))
    output = tudui(input)
    print(output.shape)

文件名train.py↓ 

import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *

#准备数据集
train_data = torchvision.datasets.CIFAR10("data",train=True,transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("data",train=False,transform=torchvision.transforms.ToTensor(),
                                         download=True)

#length 长度
train_data_size = len(train_data)
print("训练数据集的长度为：{}".format(train_data_size))
test_data_size = len(test_data)
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 = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)

#设置训练网络的一些参数

total_train_step = 0
total_test_step = 0
epoch = 10 #训练轮数
#显示地看
writer = SummaryWriter()

for i in range(epoch):
    print("--------第 {} 轮训练开始-------".format(i+1))
    #训练集
    tudui.train() #没有这行代码也能训练
    for data in train_dataloader:
        imgs,targets = data
        output = tudui(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:
            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
    tudui.eval()  # 没有这行代码也能训练
    total_test_loss = 0
    total_accuracy = 0 #整体正确率
    with torch.no_grad():
        for data in test_dataloader:
            imgs,targets = data
            output = tudui(imgs)
            loss = loss_fn(output,targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (output.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 += 1

    #模型保存
    torch.save(tudui,"tudui_{}.pth".format(1))
    #torch.save(tudui.state.dict(),"tudui_{}.pth".format(i))

writer.close()

利用GPU训练

第一种方式

#网络模型
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()


#数据
imgs,targets = data
if torch.cuda.is_available():
    imgs = imgs.cuda()
    targets = targets.cuda()

第二种方式

#定义训练的设备
device = torch.device("cpu")
#device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


#网络模型
tudui = Tudui()
tudui = tudui.to(device)

#损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)


#数据
imgs,targets = data
imgs = imgs.to(device)
targets = targets.to(device)

 完整的模型验证套路

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

img_path = "../imgs/dog.png"
image = Image.open(img_path)
print(image)
image = image.convert('RGB') #png格式有四个通道（RGB，透明通道），这一步是保留颜色通道

transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
                                            torchvision.transforms.ToTensor()])
image = transform(image)
print(image.shape)

#网络模型
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3,32,5,padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, padding=2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(1024,64),
            nn.Linear(64,10)
        )

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

#加载模型
model = torch.load("tudui_0.pth")
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))