from torch.utils.data import DataLoader,Dataset
from skimage import io,transform
import matplotlib.pyplot as plt
import oimport torch
from torchvision import transforms, utils
from PIL import Image
import pandas as pd
import numpy as np
#過濾警告信息
import warnings
warnings.filterwarnings("ignore")

class MyDataset(Dataset): #繼承Dataset
 def __init__(self, path_dir, transform=None): #初始化一些屬性
  self.path_dir = path_dir #文件路徑,如'.\data\cat-dog'
  self.transform = transform #對圖形進行處理，如標準化、截取、轉(zhuǎn)換等
  self.images = os.listdir(self.path_dir)#把路徑下的所有文件放在一個列表中
 
 def __len__(self):#返回整個數(shù)據(jù)集的大小
  return len(self.images)
 
 def __getitem__(self,index):#根據(jù)索引index返回圖像及標簽
  image_index = self.images[index]#根據(jù)索引獲取圖像文件名稱
  img_path = os.path.join(self.path_dir, image_index)#獲取圖像的路徑或目錄
  img = Image.open(img_path).convert('RGB')# 讀取圖像
    
  # 根據(jù)目錄名稱獲取圖像標簽（cat或dog）
  label = img_path.split('\\')[-1].split('.')[0]
  #把字符轉(zhuǎn)換為數(shù)字cat-0，dog-1
  label = 1 if 'dog' in label else 0
  
  if self.transform is not None:
   img = self.transform(img)
  return img,label

dataset = MyDataset('.\data\cat-dog',transform=None)
img, label = dataset[0] #將啟動魔法方法__getitem__(0)
print(type(img))
<class 'PIL.Image.Image'>

from torchvision import transforms as T
transform = T.Compose([
 T.Resize(224), # 縮放圖片(Image)，保持長寬比不變，最短邊為224像素
 T.CenterCrop(224), # 從圖片中間切出224*224的圖片
 T.ToTensor(), # 將圖片(Image)轉(zhuǎn)成Tensor，歸一化至[0, 1]
 T.Normalize(mean=[.5, .5, .5], std=[.5, .5, .5]) # 標準化至[-1, 1]，規(guī)定均值和標準差
])

dataset = MyDataset('.\data\cat-dog',transform=transform)
for img, label in dataset: 
 print("圖像img的形狀{},標簽label的值{}".format(img.shape, label))
 print("圖像數(shù)據(jù)預處理后：\n",img)
 break

#使用DataLoader加載數(shù)據(jù)
dataloader = DataLoader(dataset,batch_size=4,shuffle=True)
for batch_datas, batch_labels in dataloader:
 print(batch_datas.size(),batch_labels.size())
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([4, 3, 224, 224]) torch.Size([4])
torch.Size([2, 3, 224, 224]) torch.Size([2])

import torchvision
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
# 顯示圖像
def imshow(img):
 img = img / 2 + 0.5  # unnormalize
 npimg = img.numpy()
 plt.imshow(np.transpose(npimg, (1, 2, 0)))
 plt.show()
# 隨機獲取部分訓練數(shù)據(jù)
dataiter = iter(dataloader)
images, labels = dataiter.next()
# 顯示圖像
imshow(torchvision.utils.make_grid(images))
# 打印標簽
print(' '.join('%s' % ["小狗" if labels[j].item()==1 else "小貓" for j in range(4)]))

import torch
from torchvision import transforms, datasets
data_transform = transforms.Compose([
  transforms.RandomSizedCrop(224),
  transforms.RandomHorizontalFlip(),
  transforms.ToTensor(),
  transforms.Normalize(mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])
 ])
hymenoptera_dataset = datasets.ImageFolder(root='.\catdog\train',
           transform=data_transform)
dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,