以读取VOC2012语义分割数据集为例，具体见代码注释：
VocDataset.py
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数据集分类对应颜色标签
VOC_COLORMAP = [[0,
CamVid is provided by The University of Cambridge.本数据集由剑桥大学提供。
camvid_class_dict.csv
camvid_test_labels.zip
camvid_train_labels.zip
camvid_val.zip
camvid_test.zip
camvid_val_labels.zip
camvid_train.zip
