猫狗大战--使用 “VGG16进行CIFAR10分类” 迁移学习实现

 

猫狗大战--使用 “VGG16进行CIFAR10分类”  迁移学习实现

 

目录

 

猫狗大战--使用 “VGG16进行CIFAR10分类”  迁移学习实现

一、在colab上使用数据集

二、训练模型

三、测试数据 Valid(研习社的test在下一部分)

四、研习社测试Test

以下为旧版本  2020年11月17日 13点48分

使用VGG模型进行猫狗大战

一、代码部分

 


猫狗大战训练代码.ipynb

https://colab.research.google.com/drive/1qbo216iUiKvfnwNtVcZ2fFH821VzJoIu?usp=sharing

猫狗大战测试代码.ipynb

https://colab.research.google.com/drive/1Ulwkgn87dzDeu4nrfdIEEsyZ1YCth9Eo?usp=sharing

最优模型(Model) 百度云盘地址

链接:https://pan.baidu.com/s/1jbcO3UYiPDYRSrHpM7B7Qg   提取码:1yk2 

一、在colab上使用数据集

有两种方案:

  1. 在colab中使用wget直接从互联网下载数据
     
    ! wget *url*


     

  2. 将数据上传到Google Drive,然后在colab中连接到Drive中
     
    from google.colab import drive
    drive.mount('/content/drive')

     

 

二、训练模型

  1. 解压文件
    #具体看你自己的文件放在哪
    #1、如果是直接下载的 就默认在 conten/ 下面
    #2、用drive里的文件就在下面的路径中,可以点击左边的文件目录查看
    !unzip "/content/drive/My Drive/data.zip"

     

  2. 加载数据
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    
    vgg_format = transforms.Compose([
                    transforms.CenterCrop(224),
                    transforms.ToTensor(),
                    normalize,
                ])
    
    data_dir = '/content/data'
    
    dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
             for x in ['train']}
    
    dset_sizes = {x: len(dsets[x]) for x in ['train']}
    dset_classes = dsets['train'].classes
    
    #另一个数据集
    # data_dir2 = '/content/dogscats'
    
    # dsets2 = {x: datasets.ImageFolder(os.path.join(data_dir2, x), vgg_format)
    #          for x in ['valid']}
    
    # dset_sizes2 = {x: len(dsets2[x]) for x in ['valid']}
    # dset_classes2 = dsets2['valid'].classes
    # 通过下面代码可以查看 dsets 的一些属性
    
    print(dsets['train'].classes)
    print(dsets['train'].class_to_idx)
    print(dsets['train'].imgs[:5])
    print('dset_sizes: ', dset_sizes)
    loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=256, shuffle=True, num_workers=6)
    # loader_valid = torch.utils.data.DataLoader(dsets2['valid'], batch_size=5, shuffle=False, num_workers=6)
    # count = 1
    # for data in loader_valid:
    #     print(count, end='\n')
    #     if count == 1:
    #         inputs_try,labels_try = data
    #     count +=1
    
    # print(labels_try)
    # print(inputs_try.shape)

    注释掉的是验证集中的数据,因为这部分主要是训练,测试和验证我会跟训练分开,原因下面会介绍。

  3. 下载模型(第一次训练,需要下载VGG16的模型)
    #下载
    !wget https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json

     如果下面的运行不出来,把上面的验证集注释取消就可以了,也可以把下面报错的行全 删掉/注释 掉。

    #使用vgg16需要
    model_vgg = models.vgg16(pretrained=True)
    
    with open('./imagenet_class_index.json') as f:
        class_dict = json.load(f)
    dic_imagenet = [class_dict[str(i)][1] for i in range(len(class_dict))]
    
    inputs_try , labels_try = inputs_try.to(device), labels_try.to(device)
    model_vgg = model_vgg.to(device)
    
    outputs_try = model_vgg(inputs_try)
    
    print(outputs_try)
    print(outputs_try.shape)
    
    '''
    可以看到结果为5行,1000列的数据,每一列代表对每一种目标识别的结果。
    但是我也可以观察到,结果非常奇葩,有负数,有正数,
    为了将VGG网络输出的结果转化为对每一类的预测概率,我们把结果输入到 Softmax 函数
    '''
    m_softm = nn.Softmax(dim=1)
    probs = m_softm(outputs_try)
    vals_try,pred_try = torch.max(probs,dim=1)
    
    print( 'prob sum: ', torch.sum(probs,1))
    print( 'vals_try: ', vals_try)
    print( 'pred_try: ', pred_try)
    def imshow(inp, title=None):
    #   Imshow for Tensor.
        inp = inp.numpy().transpose((1, 2, 0))
        mean = np.array([0.485, 0.456, 0.406])
        std = np.array([0.229, 0.224, 0.225])
        inp = np.clip(std * inp + mean, 0,1)
        plt.imshow(inp)
        if title is not None:
            plt.title(title)
        plt.pause(0.001)  # pause a bit so that plots are updated
    print([dic_imagenet[i] for i in pred_try.data])
    imshow(torchvision.utils.make_grid(inputs_try.data.cpu()), 
           title=[dset_classes[x] for x in labels_try.data.cpu()])

     

  4. 修改模型
    print(model_vgg)
    
    model_vgg_new = model_vgg;
    
    #冻结VGG16中的参数,不进行梯度下降
    for param in model_vgg_new.parameters():
        param.requires_grad = False
    
    #新增两个线性层,后期主要训练这两层
    model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 4096)
    model_vgg_new.classifier._modules['7'] = nn.ReLU(inplace=False)
    model_vgg_new.classifier._modules['8'] = nn.Dropout(p=0.5,inplace=False)
    model_vgg_new.classifier._modules['9'] = nn.Linear(4096, 2)
    model_vgg_new.classifier._modules['10'] = torch.nn.LogSoftmax(dim=1)
    
    model_vgg_new = model_vgg_new.to(device)
    
    print(model_vgg_new.classifier)

     

  5. 训练模型

    ① 我把SGD改成了Adam;
    ② epochs修改到了100;
    ③ 每一个epoch结束,都会计算loss 和acc,然后把acc最高的那一时刻的model覆盖保留
    ④ 训练结束后,把最后一轮的model保留
    ⑤ model都会保留到Google Drive 中
    from tqdm import trange,tqdm
    criterion = nn.NLLLoss()
    lr = 0.001
    optimizer_vgg = torch.optim.Adam(model_vgg_new.classifier[6].parameters(), lr=lr)
    
    def train_model(model, dataloader, size, epochs=200, optimizer=None):
        model.train()
        max_acc = 0
        count = 0
        for epoch in range(epochs):
            running_loss = 0.0
            running_corrects = 0
            count = 0
            for inputs, classes in tqdm(dataloader):
                inputs = inputs.to(device)
                classes = classes.to(device)
                outputs = model(inputs)
                loss = criterion(outputs, classes)
                optimizer = optimizer
                optimizer.zero_grad()
                loss.backward()
                optimizer.step()
                _, preds = torch.max(outputs.data, 1)
                # statistics
                running_loss += loss.data.item()
                running_corrects += torch.sum(preds == classes.data)
                count += len(inputs)
                #print('Training: No. ', count, ' process ... total: ', size)
            epoch_loss = running_loss / size
            epoch_acc = running_corrects.data.item() / size
            if epoch_acc>max_acc:
                max_acc = epoch_acc
                torch.save(model, '/content/drive/My Drive/model_best_new.pth')
                tqdm.write("\n Got A Nice Model Acc:{:.8f}".format(max_acc))
            tqdm.write('\nepoch: {} \tLoss: {:.8f} Acc: {:.8f}'.format(epoch,epoch_loss, epoch_acc))
            time.sleep(0.1)
    
        torch.save(model, '/content/drive/My Drive/model_last_new.pth')
        tqdm.write("Got A Nice Model")
    
    
    # 模型训练
    train_model(model_vgg_new, loader_train, size=dset_sizes["train"], epochs=100,
                optimizer=optimizer_vgg)
    猫狗大战--使用 “VGG16进行CIFAR10分类” 迁移学习实现_第1张图片

     

三、测试数据 Valid(研习社的test在下一部分)

在上一部分,我将train和valid分开是原因的是:

  • 训练过程很慢,特别是在train和epoch都比较大的情况下,即使是用 Tesla P100 训练也需要很久
  • 因为训练时间很久,所以我将acc比较高的model都保存到了Google Drive中,这样就可以在另一个colab中直接拿到表现最好的model进行Valid了
  • 因为这样更骚。
  1. 从Google Drive 中获取model 和 测试数据
    from google.colab import drive
    drive.mount('/content/drive')
    #视具体情况而定
    !unzip "/content/drive/My Drive/test.zip"

     

  2. 加载数据和模型
    import os
    import torch
    from torchvision import transforms,datasets
    from tqdm import tqdm
    
    
    device = torch.device("cuda:0")
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    vgg_format = transforms.Compose([
                    transforms.CenterCrop(224),
                    transforms.ToTensor(),
                    normalize,
                ])
    
    
    #注意这里的文件夹名称,我的是test,因为我的压缩包就叫test
    data_dir = r'test'
    file_name = 'valid'#"train1"
    dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
             for x in [file_name]}
    
    dset_sizes = {x: len(dsets[x]) for x in [file_name]}
    
    loader_valid = torch.utils.data.DataLoader(dsets[file_name], batch_size=256, shuffle=False, num_workers=0)
    
    #这里是需要记载的模型
    model_vgg_new = torch.load(r'/content/drive/My Drive/model_best_new.pth')
    model_vgg_new = model_vgg_new.to(device)

     

  3. 测试
    def test_model(model,dataloader,size):
        model.eval()
        running_corrects = 0
        for inputs,classes in tqdm(dataloader):
            inputs = inputs.to(device)
            classes = classes.to(device)
            outputs = model(inputs)
            _,preds = torch.max(outputs.data,1)
            running_corrects += torch.sum(preds == classes.data)
        epoch_acc = running_corrects.data.item() / size
        tqdm.write('Acc: {:.4f} '.format(epoch_acc))
    
    
    test_model(model_vgg_new, loader_valid, size=dset_sizes[file_name])

     

四、研习社测试Test

  1. 加载 测试数据 和 模型
    import torch
    import numpy as np
    from torchvision import transforms,datasets
    from tqdm import tqdm
    device = torch.device("cuda:0" )
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    vgg_format = transforms.Compose([
                    transforms.CenterCrop(224),
                    transforms.ToTensor(),
                    normalize,
                ])
    
    #注意这里,我的数据在yanxishe这个文件夹里
    dsets_mine = datasets.ImageFolder(r"yanxishe", vgg_format)
    
    loader_test = torch.utils.data.DataLoader(dsets_mine, batch_size=1, shuffle=False, num_workers=0)
    
    #模型的具体地址需要根据具体情况修改
    model_vgg_new = torch.load(r'/content/drive/My Drive/model_best_16.pth')
    model_vgg_new = model_vgg_new.to(device)
    

     

  2. 测试
    dic = {}
    def test(model,dataloader,size):
        model.eval()
        predictions = np.zeros(size)
        cnt = 0
        for inputs,_ in tqdm(dataloader):
            inputs = inputs.to(device)
            outputs = model(inputs)
            _,preds = torch.max(outputs.data,1)    
            #这里是切割路径,因为dset中的数据不是按1-2000顺序排列的
            key = dsets_mine.imgs[cnt][0].split("\\")[-1].split('.')[0]
            dic[key] = preds[0]
            cnt = cnt +1
    test(model_vgg_new,loader_test,size=2000)

     
  3. 写入csv
    with open("result18.csv",'a+') as f:
        for key in range(2000):
            #这里的yanxishe/test/是我的图片路径,按需更换
            f.write("{},{}\n".format(key,dic["yanxishe/test/"+str(key)]))

     

五、结果

 

猫狗大战--使用 “VGG16进行CIFAR10分类” 迁移学习实现_第2张图片

以下为旧版本  2020年11月17日 13点48分


使用VGG模型进行猫狗大战

原文见:https://github.com/mlelarge/dataflowr/blob/master/CEA_EDF_INRIA/01_intro_DLDIY_colab.ipynb

 

  • VGG是由Simonyan 和Zisserman在文献《Very Deep Convolutional Networks for Large Scale Image Recognition》中提出卷积神经网络模型,其名称来源于作者所在的牛津大学视觉几何组(Visual Geometry Group)的缩写。该模型参加2014年的 ImageNet图像分类与定位挑战赛,取得了优异成绩:在分类任务上排名第二,在定位任务上排名第一。

  • 迁移学习是一种机器学习方法,就是把为任务 A 开发的模型作为初始点,重新使用在为任务 B 开发模型的过程中。

  • ImageNet图像分类10类中存在猫和狗,所以用VGG来作为“猫狗大战”的预训练是十分合理的

一、代码部分

  • 头文件
import os
import torch
import torch.nn as nn
from torchvision import models,transforms,datasets
from tqdm import trange,tqdm

# 判断是否存在GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print('Using gpu: %s ' % torch.cuda.is_available())
  • 数据处理

datasets 是 torchvision 中的一个包,可以用做加载图像数据。它可以以多线程(multi-thread)的形式从硬盘中读取数据,使用 mini-batch 的形式,在网络训练中向 GPU 输送。在使用CNN处理图像时,需要进行预处理。图片将被整理成 224*224*3 的大小,同时还将进行归一化处理。

这里我将https://static.leiphone.com/cat_dog.rar的训练文件一起加入了到了训练集中,因为原来的训练集只有1800张图片,我希望能在更大的数据集上进行训练,以求获得更好的结果。


normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

vgg_format = transforms.Compose([
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                normalize,
            ])

data_dir = r'G:\作业\#1.人工智能\colab_demo-master\dogscats'

dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
         for x in ['train', 'valid']}

dset_sizes = {x: len(dsets[x]) for x in ['train', 'valid']}
dset_classes = dsets['train'].classes

loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=40, shuffle=True, num_workers=0)
loader_valid = torch.utils.data.DataLoader(dsets['valid'], batch_size=16, shuffle=False, num_workers=0)
  •  载入 VGG Model 

这里我把训练出来比较好的模型序列化到硬盘上

首先,准确率比较高的情况往往不是训练的最终结果,选择准确率较高的模型保存到本地可以获得比较好的效果

其次,2w+数据的训练周期较长,拿出其中表现较好时刻的模型可以提前进行测试,提高效率

n = input("是否重新训练?(Y/N)")
if n=='N':
    path = input("输入文件名:")
    CNT = input("输入轮数:")
    model_vgg_new = torch.load(path)
    model_vgg_new = model_vgg_new.to(device)
else:
    model_vgg = models.vgg16(pretrained=True)
    model_vgg = model_vgg.to(device)
    model_vgg_new = model_vgg

    for param in model_vgg_new.parameters():
        param.requires_grad = False
    model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 2)
    model_vgg_new.classifier._modules['7'] = torch.nn.LogSoftmax(dim = 1)
  •  训练并测试全连接层

将表现较好时刻的模型存盘到本地

model_vgg_new = model_vgg_new.to(device)

criterion = nn.NLLLoss()

# 学习率
lr = 0.001


optimizer_vgg = torch.optim.Adam(model_vgg_new.classifier[6].parameters(), lr=lr)

'''
第二步:训练模型
'''
N_ = int(CNT)+1


def train_model(model, dataloader, size, epochs=100, optimizer=None):
    model.train()
    global N_
    for epoch in range(epochs):
        running_loss = 0.0
        running_corrects = 0
        count = 0
        for inputs, classes in tqdm(dataloader):
            inputs = inputs.to(device)
            classes = classes.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, classes)
            optimizer = optimizer
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            _, preds = torch.max(outputs.data, 1)
            # statistics
            running_loss += loss.data.item()
            running_corrects += torch.sum(preds == classes.data)
            count += len(inputs)
            #print('Training: No. ', count, ' process ... total: ', size)
        epoch_loss = running_loss / size
        epoch_acc = running_corrects.data.item() / size
        print('{} \tLoss: {:.4f} Acc: {:.4f}'.format(N_,epoch_loss, epoch_acc))
        if epoch_acc > 0.97:
            torch.save(model, './model'+str(N_)+'_'+str(epoch_acc)+'_'+'.pth')
            print("Got A Nice Model")
        N_ = N_ + 1


# 模型训练
train_model(model_vgg_new, loader_train, size=dset_sizes['train'], epochs=100,
            optimizer=optimizer_vgg)
  • 训练过程

猫狗大战--使用 “VGG16进行CIFAR10分类” 迁移学习实现_第3张图片

  • AI研习社结果

猫狗大战--使用 “VGG16进行CIFAR10分类” 迁移学习实现_第4张图片

  • 测试代码
import os
import torch
from torchvision import transforms,datasets
from tqdm import tqdm


device = torch.device("cuda:0")
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                normalize,
            ])

data_dir = r'G:\作业\#1.人工智能\colab_demo-master\dogscats'

dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
         for x in ['valid']}

dset_sizes = {x: len(dsets[x]) for x in ['valid']}

loader_valid = torch.utils.data.DataLoader(dsets['valid'], batch_size=8, shuffle=False, num_workers=0)

model_vgg_new = torch.load('xxxxxx')
model_vgg_new = model_vgg_new.to(device)

def test_model(model,dataloader,size):
    model.eval()
    running_corrects = 0
    for inputs,classes in tqdm(dataloader):
        inputs = inputs.to(device)
        classes = classes.to(device)
        outputs = model(inputs)
        _,preds = torch.max(outputs.data,1)
        running_corrects += torch.sum(preds == classes.data)
    epoch_acc = running_corrects.data.item() / size
    print('Acc: {:.4f} '.format(epoch_acc))


test_model(model_vgg_new, loader_valid, size=dset_sizes['valid'])
  • 研习社数据测试代码
import torch
import numpy as np
from torchvision import transforms,datasets
from tqdm import tqdm
device = torch.device("cuda:0" )
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                normalize,
            ])
dsets_mine = datasets.ImageFolder(r"G:\作业\#1.人工智能\colab_demo-master\dogscats2", vgg_format)

loader_test = torch.utils.data.DataLoader(dsets_mine, batch_size=1, shuffle=False, num_workers=0)

model_vgg_new = torch.load('')
model_vgg_new = model_vgg_new.to(device)

dic = {}
def test(model,dataloader,size):
    model.eval()
    predictions = np.zeros(size)
    cnt = 0
    for inputs,_ in tqdm(dataloader):
        inputs = inputs.to(device)
        outputs = model(inputs)
        _,preds = torch.max(outputs.data,1)
        key = dsets_mine.imgs[cnt][0].split("\\")[-1].split('.')[0]
        dic[key] = preds[0]
        cnt = cnt +1
test(model_vgg_new,loader_test,size=2000)

with open("result.csv",'a+') as f:
    for key in range(2000):
        f.write("{},{}\n".format(key,dic[str(key)]))

 

 

你可能感兴趣的:(人工智能,pytorch,深度学习)