from PIL import Image
import torch
import torch.utils.data as data
import numpy as np
import os
import torchvision
import torchvision.transforms as transforms
import time

#VOC數(shù)據(jù)集分類對應(yīng)顏色標簽
VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
        [0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
        [64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
        [64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
        [0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
        [0, 64, 128]]

#顏色標簽空間轉(zhuǎn)到序號標簽空間，就他媽這里浪費巨量的時間,這里還他媽的有問題
def voc_label_indices(colormap, colormap2label):
  """Assign label indices for Pascal VOC2012 Dataset."""
  idx = ((colormap[:, :, 2] * 256 + colormap[ :, :,1]) * 256+ colormap[:, :,0])
  #out = np.empty(idx.shape, dtype = np.int64) 
  out = colormap2label[idx]
  out=out.astype(np.int64)#數(shù)據(jù)類型轉(zhuǎn)換
  end = time.time()
  return out

class MyDataset(data.Dataset):#創(chuàng)建自定義的數(shù)據(jù)讀取類
  def __init__(self, root, is_train, crop_size=(320,480)):
    self.rgb_mean =(0.485, 0.456, 0.406)
    self.rgb_std = (0.229, 0.224, 0.225)
    self.root=root
    self.crop_size=crop_size
    images = []#創(chuàng)建空列表存文件名稱
    txt_fname = '%s/ImageSets/Segmentation/%s' % (root, 'train.txt' if is_train else 'val.txt')
    with open(txt_fname, 'r') as f:
      self.images = f.read().split()
    #數(shù)據(jù)名稱整理
    self.files = []
    for name in self.images:
      img_file = os.path.join(self.root, "JPEGImages/%s.jpg" % name)
      label_file = os.path.join(self.root, "SegmentationClass/%s.png" % name)
      self.files.append({
        "img": img_file,
        "label": label_file,
        "name": name
      })
    self.colormap2label = np.zeros(256**3)
    #整個循環(huán)的意思就是將顏色標簽映射為單通道的數(shù)組索引
    for i, cm in enumerate(VOC_COLORMAP):
      self.colormap2label[(cm[2] * 256 + cm[1]) * 256 + cm[0]] = i
  #按照索引讀取每個元素的具體內(nèi)容
  def __getitem__(self, index):
    
    datafiles = self.files[index]
    name = datafiles["name"]
    image = Image.open(datafiles["img"])
    label = Image.open(datafiles["label"]).convert('RGB')#打開的是PNG格式的圖片要轉(zhuǎn)到rgb的格式下，不然結(jié)果會比較要命
    #以圖像中心為中心截取固定大小圖像，小于固定大小的圖像則自動填0
    imgCenterCrop = transforms.Compose([
       transforms.CenterCrop(self.crop_size),
       transforms.ToTensor(),
       transforms.Normalize(self.rgb_mean, self.rgb_std),#圖像數(shù)據(jù)正則化
     ])
    labelCenterCrop = transforms.CenterCrop(self.crop_size)
    cropImage=imgCenterCrop(image)
    croplabel=labelCenterCrop(label)
    croplabel=torch.from_numpy(np.array(croplabel)).long()#把標簽數(shù)據(jù)類型轉(zhuǎn)為torch
    
    #將顏色標簽圖轉(zhuǎn)為序號標簽圖
    mylabel=voc_label_indices(croplabel, self.colormap2label)
    
    return cropImage,mylabel
  #返回圖像數(shù)據(jù)長度
  def __len__(self):
    return len(self.files)

import matplotlib.pyplot as plt
import torch.utils.data as data
import torchvision.transforms as transforms
import numpy as np

from PIL import Image
from VocDataset import MyDataset

#VOC數(shù)據(jù)集分類對應(yīng)顏色標簽
VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
        [0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
        [64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
        [64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
        [0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
        [0, 64, 128]]

root='../data/VOCdevkit/VOC2012'
train_data=MyDataset(root,True)
trainloader = data.DataLoader(train_data, 4)

#從數(shù)據(jù)集中拿出一個批次的數(shù)據(jù)
for i, data in enumerate(trainloader):
  getimgs, labels= data
  img = transforms.ToPILImage()(getimgs[0])

  labels = labels.numpy()#tensor轉(zhuǎn)numpy
  labels=labels[0]#獲得批次標簽集中的一張標簽圖像
  labels = labels.transpose((1,0))#數(shù)組維度切換，將第1維換到第0維，第0維換到第1維

  ##將單通道索引標簽圖片映射回顏色標簽圖片
  newIm= Image.new('RGB', (480, 320))#創(chuàng)建一張與標簽大小相同的圖片，用以顯示標簽所對應(yīng)的顏色
  for i in range(0, 480):
    for j in range(0, 320):
      sele=labels[i][j]#取得坐標點對應(yīng)像素的值
      newIm.putpixel((i, j), (int(VOC_COLORMAP[sele][0]), int(VOC_COLORMAP[sele][1]), int(VOC_COLORMAP[sele][2])))

  #顯示圖像和標簽
  plt.figure("image")
  ax1 = plt.subplot(1,2,1)
  ax2 = plt.subplot(1,2,2)
  plt.sca(ax1)
  plt.imshow(img)
  plt.sca(ax2)
  plt.imshow(newIm)
  plt.show()