! wget https://static.leiphone.COM/cat_dog.rar
! unrar x cat_dog.rar

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,
            ])

#这里进行了修改，包括训练数据、验证数据、以及测试数据，分别在三个目录train/val/test
import shutil
data_dir = './cat_dog'
os.mkdir("./cat_dog/train/cat")
os.mkdir("./cat_dog/train/dog")
os.mkdir("./cat_dog/val/cat")
os.mkdir("./cat_dog/val/dog")
for i in range(10000):
  cat_name = './cat_dog/train/cat_'+str(i)+'.jpg';
  dog_name = './cat_dog/train/dog_'+str(i)+'.jpg';
  shutil.move(cat_name,"./cat_dog/train/cat")
  shutil.move(dog_name,"./cat_dog/train/dog")

for i in range(1000):
  cat_name = './cat_dog/val/cat_'+str(i)+'.jpg';
  dog_name = './cat_dog/val/dog_'+str(i)+'.jpg';
  shutil.move(cat_name,"./cat_dog/val/cat")
  shutil.move(dog_name,"./cat_dog/val/dog")
#读取测试问题的数据集

test_path = "./cat_dog/test/dogs_cats"
os.mkdir(test_path)
#移动到test_path
for i in range(2000):
  name = './cat_dog/test/'+str(i)+'.jpg' 
  shutil.move(name,"./cat_dog/test/dogs_cats")

file_list=os.listdir("./cat_dog/test/dogs_cats")
#将图片名补全，防止读取顺序不对
for file in file_list:
  #填充0后名字总共10位，包括扩展名
  filename = file.zfill(10)
  new_name =''.join(filename)
  os.rename(test_path+'/'+file,test_path+'/'+new_name)
#将所有图片数据放到dsets内
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
loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=64, shuffle=True, num_workers=6)
loader_valid = torch.utils.data.DataLoader(dsets['val'], batch_size=5, shuffle=False, num_workers=6)
#加入测试集
loader_test = torch.utils.data.DataLoader(dsets['test'], batch_size=5,shuffle=False, num_workers=6)

'''
valid 数据一共有2000张图，每个batch是5张，因此，下面进行遍历一共会输出到 400
同时，把第一个 batch 保存到 inputs_try, labels_try，分别查看
'''
count = 1
for data in loader_test:
    PRint(count, end=',')
    if count%50==0: 
      print()
    if count == 1:
        inputs_try,labels_try = data
    count +=1

print(labels_try)
print(inputs_try.Shape)

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)

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()])

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)

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)