Pytorch卷积神经网络迁移学习的目标及好处

import torch
import torchvision as tv
import torch.nn as nn
import torchvision
import torch.nn.functional as F
import torchvision.transforms as transforms
import torch
from torch.utils import data
from torch import optim
from torch.autograd import Variable
model_name='resnet'
featuer_extract=True
train_on_gpu=torch.cuda.is_available()
if not train_on_gpu:
    print("没有gpu")
else :
    print("是gpu")
devic=torch.device("cuda:0" if torch.cuda.is_available() else 'cpu')
teature_extract=True
def set_paremeter_requires_grad(model,featuer_extract):
    if featuer_extract:
        for parm in model.parameters():
            parm.requires_grad=False   #不做训练
def initialize_model(model_name,num_classes,featuer_extract,use_pretrained=True):
    model_ft = None
    input_size = 0
    if model_name=="resnet":
        model_ft=tv.models.resnet152(pretrained=use_pretrained)#下载模型
        set_paremeter_requires_grad(model_ft,featuer_extract) #冻结层数
        num_ftrs=model_ft.fc.in_features #改动全连接层
        model_ft.fc=nn.Sequential(nn.Linear(num_ftrs,num_classes),
                                  nn.LogSoftmax(dim=1))
        input_size=224 #输入维度
    return  model_ft,input_size
model_ft,iput_size=initialize_model(model_name,10,featuer_extract,use_pretrained=True)
model_ft=model_ft.to(devic)
params_to_updata=model_ft.parameters()
if featuer_extract:
    params_to_updata=[]
    for name,param in model_ft.named_parameters():
        if param.requires_grad==True:
            params_to_updata.append(param)
            print("\t",name)
else:
    for name,param in model_ft.parameters():
        if param.requires_grad==True:
            print("\t",name)
opt=optim.Adam(params_to_updata,lr=0.01)
loss=nn.NLLLoss()
if __name__ == '__main__':
    transform = transforms.Compose([
        # 图像增强
        transforms.Resize(1024),#裁剪
        transforms.RandomHorizontalFlip(),#随机水平翻转
        transforms.RandomCrop(224),#随机裁剪
        transforms.ColorJitter(brightness=0.5, contrast=0.5, hue=0.5), #亮度
        # 转变为tensor 正则化
        transforms.ToTensor(), #转换格式
        transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))  # 归一化处理
    ])
    trainset = tv.datasets.CIFAR10(
        root=r'E:\桌面\资料\cv3\数据集\cifar-10-batches-py',
        train=True,
        download=True,
        transform=transform
    )
    trainloader = data.DataLoader(
        trainset,
        batch_size=8,
        drop_last=True,
        shuffle=True,  # 乱序
        num_workers=4,
    )
    testset = tv.datasets.CIFAR10(
        root=r'E:\桌面\资料\cv3\数据集\cifar-10-batches-py',
        train=False,
        download=True,
        transform=transform
    )
    testloader = data.DataLoader(
        testset,
        batch_size=8,
        drop_last=True,
        shuffle=False,
        num_workers=4
    )
    for epoch in range(3):
        running_loss=0
        for index,data in enumerate(trainloader,0):
            inputs, labels = data
            inputs = inputs.to(devic)
            labels = labels.to(devic)
            inputs, labels = Variable(inputs), Variable(labels)
            opt.zero_grad()
            h=model_ft(inputs)
            loss1=loss(h,labels)
            loss1.backward()
            opt.step()
            h+=loss1.item()
            if index%10==9:
                avg_loss=loss1/10.
                running_loss=0
                print('avg_loss',avg_loss)
            if index%100==99 :
                correct=0
                total=0
                for data in testloader:
                    images,labels=data
                    outputs=model_ft(Variable(images.cuda()))
                    _,predicted=torch.max(outputs.cpu(),1)
                    total+=labels.size(0)
                    bool_tensor=(predicted==labels)
                    correct+=bool_tensor.sum()
                print('1000张测试集中的准确率为%d   %%'%(100*correct/total))