VGG训练猫狗大战

1.下载并导入数据集

下载地址：https://static.leiphone.com/cat_dog.rar

导入工作：

　　1）首先是导入谷歌云盘（花费时间较长）

　　2）将导入的数据连接到Colab项目中

代码如下：

!apt-get install -y -qq software-properties-common python-software-properties module-init-tools
!add-apt-repository -y ppa:alessandro-strada/ppa 2>&1 > /dev/null
!apt-get update -qq 2>&1 > /dev/null
!apt-get -y install -qq google-drive-ocamlfuse fuse
from google.colab import auth
auth.authenticate_user()
from oauth2client.client import GoogleCredentials
creds = GoogleCredentials.get_application_default()
import getpass
!google-drive-ocamlfuse -headless -id={creds.client_id} -secret={creds.client_secret} < /dev/null 2>&1 | grep URL
vcode = getpass.getpass()
!echo {vcode} | google-drive-ocamlfuse -headless -id={creds.client_id} -secret={creds.client_secret}

!mkdir -p drive
!google-drive-ocamlfuse drive

 发现文件中出现drive/cat_dog文件

（后来发现可以直接在文件中选择装载谷歌云硬盘，效果相同）

2.制作dataloader并将设备运行到gpu上

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print('Using gpu: %s ' % torch.cuda.is_available())
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/drive/cat_dog /cat_dog'

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

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

 

 这部分代码写法与之前相似，但在导入图片文件时报错，错误原因为地址错误，发现需要在原本的test和val文件夹之上再创建一个test和val，原因未明。

 

3.验证导入图片是否成功（val中的前五张图片）

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)  

out = torchvision.utils.make_grid(inputs_try)
imshow(out, title=[dset_classes[x] for x in labels_try])

 

 

 

 

4.下载预训练模型：

!wget https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json

 

5.使用预训练模型对以上五张图片进行检测

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)

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)

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()]) 

 

发现预测成功率很高。 

6.打印观察网络结构，并修改最后一层为两类（猫/狗）

print(model_vgg)

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)

model_vgg_new = model_vgg_new.to(device)

print(model_vgg_new.classifier)

  

    

  

7.训练模型：

criterion = nn.NLLLoss()

# 学习率
lr = 0.001

# 随机梯度下降
optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr)

'''
第二步：训练模型
'''

def train_model(model,dataloader,size,epochs=1,optimizer=None):
    model.train()
    
    for epoch in range(epochs):
        running_loss = 0.0
        running_corrects = 0
        count = 0
        for inputs,classes in 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('Loss: {:.4f} Acc: {:.4f}'.format(
                     epoch_loss, epoch_acc))
        
        
# 模型训练
train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1, 
            optimizer=optimizer_vgg)

 

 

 

8.用val集进行测试

def test_model(model,dataloader,size):
    model.eval()
    predictions = np.zeros(size)
    all_classes = np.zeros(size)
    all_proba = np.zeros((size,2))
    i = 0
    running_loss = 0.0
    running_corrects = 0
    for inputs,classes in dataloader:
        inputs = inputs.to(device)
        classes = classes.to(device)
        outputs = model(inputs)
        loss = criterion(outputs,classes)           
        _,preds = torch.max(outputs.data,1)
        # statistics
        running_loss += loss.data.item()
        running_corrects += torch.sum(preds == classes.data)
        predictions[i:i+len(classes)] = preds.to('cpu').numpy()
        all_classes[i:i+len(classes)] = classes.to('cpu').numpy()
        all_proba[i:i+len(classes),:] = outputs.data.to('cpu').numpy()
        i += len(classes)
        print('Testing: No. ', i, ' process ... total: ', size)        
    epoch_loss = running_loss / size
    epoch_acc = running_corrects.data.item() / size
    print('Loss: {:.4f} Acc: {:.4f}'.format(
                     epoch_loss, epoch_acc))
    return predictions, all_proba, all_classes
  
predictions, all_proba, all

 

测试通过率很高

 

9.可视化模型训练结果：

import numpy as np

n_view = 8
correct = np.where(predictions==all_classes)[0]
from numpy.random import random, permutation
idx = permutation(correct)[:n_view]
print('random correct idx: ', idx)
loader_correct = torch.utils.data.DataLoader([dsets['val'][x] for x in idx],
                  batch_size = n_view,shuffle=True)
for data in loader_correct:
    inputs_cor,labels_cor = data
# Make a grid from batch
out = torchvision.utils.make_grid(inputs_cor)
imshow(out, title=[l.item() for l in labels_cor])

 

 

10.制作csv并上传ai研习社 

import csv
with open('/content/drive/cat_dog /cat_dog2.csv','w',newline="")as f:
  writer = csv.writer(f)
  for index,cls in enumerate(predictions):
    path = datasets.ImageFolder(os.path.join(data_dir,'test'),vgg_format).imgs[index][0]
    l = path.split("/")
    img_name = l[-1]
    order = int(img_name.split(".")[0])
    writer.writerow([order,int(predictions[index])])

 发现分数过低，正在查找问题。