Pytorch自定义dataloader以及在迭代过程中返回image的name

pytorch官方给的加载数据的方式是已经定义好的dataset以及loader，如何加载自己本地的图片以及label？

形如数据格式为

image1 label1

image2 label2

...

imagen labeln

实验中我采用的数据的格式如下，一个图片的名字对应一个ｌａｂｅｌ，每一个ｌａｂｅｌ是一个９维的向量

1_-2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.304295635957 0.952577642997 0.0614006041909 0.0938333659301 -0.995587916479 0.126405046864 -0.999368204665 0.0355414055005 0.382030624629 0.0
1_0_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.271224474168 0.962516121742 0.061399602839 0.128727689658 -0.991679979588 0.126495313272 -0.999999890616 0.000467726796359 0.381981952872 0.0
1_2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.237868729379 0.971297311632 0.0614713240576 0.163626102983 -0.986522426721 0.1265439964 -0.999400990041 -0.0346072406472 0.382020891324 0.0
1.1_-2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.303575822293 0.95280728383 0.0675229548933 0.0939225945957 -0.995579502714 0.138745857429 -0.999376861795 0.0352971402251 0.410670255038 0.1
1.1_0_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.270745576918 0.962650940154 0.0674654115238 0.128659340525 -0.991688849436 0.138685653232 -0.999999909615 0.000425170029598 0.410739827476 0.1
1.1_2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.23757921143 0.971368168253 0.0674866175928 0.16322766122 -0.986588430204 0.138789623782 -0.999406504329 -0.0344476284471 0.410661183171 0.1
1.2_-2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.305474635089 0.952200213882 0.0736939767933 0.0939968709874 -0.995572492712 0.150981626608 -0.999370773952 0.0354690875311 0.437620875774 0.2
1.2_0_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.270346113421 0.962763199836 0.073518963401 0.128433455959 -0.991718129002 0.150964425444 -0.999999924062 0.000389711583812 0.437667827367 0.2
1.2_2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.237337349604 0.971427291403 0.0734898449879 0.162895476227 -0.986643331617 0.150931800731 -0.999411541516 -0.0343011761519 0.437608139736 0.2
1.3_-2_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.305514664536 0.952187371137 0.0795990377393 0.0941741911595 -0.995555735115 0.162914965783 -0.999378340534 0.0352552474342 0.462816755558 0.3
1.3_0_pitch_100_yaw_0_lat_29.7553171_lng_-95.3675684.jpg 0.272366931798 0.962193459998 0.0796135882128 0.128398130503 -0.991722703221 0.162940731132 -0.999999935257 0.000359841646368 0.462733965419 0.3

．．．

源程序如下

 import torch
 import torch.nn as nn
 import math
 import os
 from PIL import Image
 import random
 from torchvision import datasets, transforms
 import torch.utils.data as data
 from torch.autograd import Variable

 torch.cuda.set_device(0)
 # os.environ["CUDA_VISIBLE_DEVICES"] = "1"
 kwargs = {'num_workers': 1, 'pin_memory': True}
 batch_size = 8
 # load the data
 def random_choose_data(label_path):
     random.seed(1)
     file = open(label_path)
     lines = file.readlines()
     slice_initial = random.sample(lines, 200000)  # if don't change this ,it will be all the same
     slice = list(set(lines)-set(slice_initial))
     random.shuffle(slice)

     train_label = slice[:150000]
     test_label = slice[150000:200000]
     return train_label, test_label  # output the list and delvery it into ImageFolder

 # def my data loader, return the data and corresponding label
 def default_loader(path):
     return Image.open(path).convert('RGB')  # operation object is the PIL image object

 class myImageFloder(data.Dataset):  # Class inheritance
     def __init__(self, root, label, transform=None, target_transform=None, loader=default_loader):
         # fh = open(label)
         c = 0
         imgs = []
         class_names = ['regression']
         for line in label:  # label is a list
             cls = line.split()  # cls is a list
             fn = cls.pop(0)
             if os.path.isfile(os.path.join(root, fn)):
                 imgs.append((fn, tuple([float(v) for v in cls[:len(cls)-1]])))
                 # access the last label
                 # images is the list,and the content is the tuple, every image corresponds to a label
                 # despite the label's dimension
                 # we can use the append way to append the element for list
             c = c + 1
         print('the total image is',c)
         print(class_names)
         self.root = root
         self.imgs = imgs
         self.classes = class_names
         self.transform = transform
         self.target_transform = target_transform
         self.loader = loader
     def __getitem__(self, index):
         fn, label = self.imgs[index]  # even though the imgs is just a list, it can return the elements of it
         # in a proper way
         img = self.loader(os.path.join(self.root, fn))
         if self.transform is not None:
             img = self.transform(img)
         return img, torch.Tensor(label), fn

     def __len__(self):
         return len(self.imgs)

     def getName(self):
         return self.classes

 mytransform = transforms.Compose([transforms.ToTensor()])  # transform [0,255] to [0,1]
 test_data_root = "/home/ying/data/google_streetview_train_test1"
 data_label = "/home/ying/data/google_streetview_train_test1/label.txt"
 # test_label="/home/ying/data/google_streetview_train_test1/label.txt"
 train_label, test_label = random_choose_data(data_label)
 test_loader = torch.utils.data.DataLoader(
          myImageFloder(root=test_data_root, label=test_label, transform=mytransform),batch_size=batch_size, shuffle=True, **kwargs)

 def conv3x3(in_planes, out_planes, stride=1):
     "3x3 convolution with padding"
     return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                      padding=1, bias=False)

 class BasicBlock(nn.Module):
     expansion = 1

     def __init__(self, inplanes, planes, stride=1, downsample=None):
         super(BasicBlock, self).__init__()
         self.conv1 = conv3x3(inplanes, planes, stride)
         self.bn1 = nn.BatchNorm2d(planes)
         self.relu = nn.ReLU(inplace=True)
         self.conv2 = conv3x3(planes, planes)
         self.bn2 = nn.BatchNorm2d(planes)
         self.downsample = downsample
         self.stride = stride

     def forward(self, x):
         residual = x

         out = self.conv1(x)
         out = self.bn1(out)
         out = self.relu(out)

         out = self.conv2(out)
         out = self.bn2(out)

         if self.downsample is not None:
             residual = self.downsample(x)

         out += residual
         out = self.relu(out)

         return out

 class Bottleneck(nn.Module):
     expansion = 4

     def __init__(self, inplanes, planes, stride=1, downsample=None):
         super(Bottleneck, self).__init__()
         self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)  # decrease the channel, does't change size
         self.bn1 = nn.BatchNorm2d(planes)
         self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                                padding=1, bias=False)
         self.bn2 = nn.BatchNorm2d(planes)
         self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
         self.bn3 = nn.BatchNorm2d(planes * 4)
         self.relu = nn.ReLU(inplace=True)
         self.downsample = downsample
         self.stride = stride

     def forward(self, x):
         residual = x

         out = self.conv1(x)
         out = self.bn1(out)
         out = self.relu(out)

         out = self.conv2(out)
         out = self.bn2(out)
         out = self.relu(out)

         out = self.conv3(out)
         out = self.bn3(out)

         if self.downsample is not None:
             residual = self.downsample(x)

         out += residual
         out = self.relu(out)

         return out

 class ResNet(nn.Module):

     def __init__(self, block, layers, num_classes=9):
         self.inplanes = 64
         super(ResNet, self).__init__()
         self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                                bias=False)  # the size become 1/2
         self.bn1 = nn.BatchNorm2d(64)
         self.relu = nn.ReLU(inplace=True)
         self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)  # the size become 1/2
         self.layer1 = self._make_layer(block, 64, layers[0])
         self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
         self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
         self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
         self.avgpool = nn.AvgPool2d(7)
         # self.fc = nn.Linear(512 * block.expansion, num_classes)
         self.fc = nn.Linear(2048, num_classes)

         for m in self.modules():
             if isinstance(m, nn.Conv2d):
                 n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                 m.weight.data.normal_(0, math.sqrt(2. / n))
             elif isinstance(m, nn.BatchNorm2d):
                 m.weight.data.fill_(1)
                 m.bias.data.zero_()

     def _make_layer(self, block, planes, blocks, stride=1):
         #  block: object, planes: output channel, blocks: the num of blocks
         downsample = None
         if stride != 1 or self.inplanes != planes * block.expansion:
             downsample = nn.Sequential(
                 nn.Conv2d(self.inplanes, planes * block.expansion,
                           kernel_size=1, stride=stride, bias=False),
                 nn.BatchNorm2d(planes * block.expansion),
             )

         layers = []
         layers.append(block(self.inplanes, planes, stride, downsample))
         self.inplanes = planes * block.expansion  # the input channel num become 4 times
         for i in range(1, blocks):
             layers.append(block(self.inplanes, planes))

         return nn.Sequential(*layers)

     def forward(self, x):
         x = self.conv1(x)
         x = self.bn1(x)
         x = self.relu(x)
         x = self.maxpool(x)

         x = self.layer1(x)
         x = self.layer2(x)
         x = self.layer3(x)
         x = self.layer4(x)

         x = self.avgpool(x)
         x = x.view(x.size(0), -1)
         x = self.fc(x)
         return x

 def resnet50(pretrained = True):
     """Constructs a ResNet-50 model.

     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
     """
     model = ResNet(Bottleneck, [3, 4, 6, 3])
     # model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
     model.load_state_dict(torch.load('./resnet50_20170907_state_dict.pth'))
     return model
 cnn = resnet50(pretrained=True)  # the output number is 9
 cnn.cuda()
 cnn.eval()
 criterion = nn.MSELoss().cuda()

 for i, (test_images, test_labels, fn) in enumerate(test_loader):  # the first i in index, and the () is the content
     test_images = Variable(test_images.cuda())
     test_labels = Variable(test_labels.cuda())
     outputs = cnn(test_images)
     print(outputs.data[0])
     print(fn)
     loss = criterion(outputs, test_labels)
     print("Iter [%d/%d] Test_Loss: %.4f" % (i + 1, 781, loss.data[0]))

着重看定义ｄａｔａｌｏａｄｅｒ以及返回图像名称的一段代码：

 def random_choose_data(label_path):
     random.seed(1)
     file = open(label_path)
     lines = file.readlines()
     slice_initial = random.sample(lines, 200000)  # if don't change this ,it will be all the same
     slice = list(set(lines)-set(slice_initial))
     random.shuffle(slice)

     train_label = slice[:150000]
     test_label = slice[150000:200000]
     return train_label, test_label  # output the list and delvery it into ImageFolder

 # def my data loader, return the data and corresponding label
 def default_loader(path):
     return Image.open(path).convert('RGB')  # operation object is the PIL image object

 class myImageFloder(data.Dataset):  # Class inheritance，继承Ｄａｔａｓｅｔ类
     def __init__(self, root, label, transform=None, target_transform=None, loader=default_loader):
         # fh = open(label)
         c = 0
         imgs = []
         class_names = ['regression']
         for line in label:  # label is a list
             cls = line.split()  # cls is a list
             fn = cls.pop(0)
             if os.path.isfile(os.path.join(root, fn)):
                 imgs.append((fn, tuple([float(v) for v in cls[:len(cls)-1]])))
                 # access the last label
                 # images is the list,and the content is the tuple, every image corresponds to a label
                 # despite the label's dimension
                 # we can use the append way to append the element for list
             c = c + 1
         print('the total image is',c)
         print(class_names)
         self.root = root
         self.imgs = imgs
         self.classes = class_names
         self.transform = transform
         self.target_transform = target_transform
         self.loader = loader
     def __getitem__(self, index):
         fn, label = self.imgs[index]  # even though the imgs is just a list, it can return the elements of it
         # in a proper way
         img = self.loader(os.path.join(self.root, fn))
         if self.transform is not None:
             img = self.transform(img)
         return img, torch.Tensor(label), fn　　#　在这里返回图像数据以及对应的ｌａｂｅｌ以及对应的名称

     def __len__(self):
         return len(self.imgs)

     def getName(self):
         return self.classes

实际上是继承Ｄａｔａｓｅｔ这个类中的两个函数__getitem__与__len__，并且返回的变量类型是ｔｏｒｃｈ．Ｔｅｎｓｏｒ即可

看ｄａｔａｌｏａｄｅｒ定义方式以及如何在ｄａｔａｌｏａｄｅｒ中加载数据

 mytransform = transforms.Compose([transforms.ToTensor()])  # transform [0,255] to [0,1]
 test_data_root = "/home/ying/data/google_streetview_train_test1"
 data_label = "/home/ying/data/google_streetview_train_test1/label.txt"
 # test_label="/home/ying/data/google_streetview_train_test1/label.txt"
 train_label, test_label = random_choose_data(data_label)
 test_loader = torch.utils.data.DataLoader(
          myImageFloder(root=test_data_root, label=test_label, transform=mytransform),batch_size=batch_size, shuffle=True, **kwargs)
 ．．．
 for i, (test_images, test_labels, fn) in enumerate(test_loader):  # the first i in index, and the () is the content
     test_images = Variable(test_images.cuda())
     test_labels = Variable(test_labels.cuda())
     outputs = cnn(test_images)
     print(outputs.data[0])
     print(fn)
     loss = criterion(outputs, test_labels)
     print("Iter [%d/%d] Test_Loss: %.4f" % (i + 1, 781, loss.data[0]))

实际上刚刚在myImageFloder中定义的__getitem__实际上就是i, (test_images, test_labels, fn) in enumerate(test_loader): 中返回的对象，　其中第一个ｉ是与ｅｎｕｍｂｅｒａｔｅ相关的ｉｎｄｅｘ

这样就能够在模型ｔｅｓｔ的时候观察哪些数据误差比较大并且进行输出