-1

我正在尝试使用 pytorch 学习 One-shot 学习。我正在Pytorch 示例中试验这个连体网络。使用该笔记本作为指南，我只想打印出每对图像的图像文件路径，以及相异性分数。

从我一直在阅读的内容来看，我需要对数据加载器进行一些更改才能实现这一点，如此处所示。

我在这一切方面还没有太多经验。我会很感激一些指导。我将更改后的数据加载器（如本要点）导入到我的代码中。

更改后的数据加载器：

import torch
from torchvision import datasets

class ImageFolderWithPaths(datasets.ImageFolder):
    """Custom dataset that includes image file paths. Extends
    torchvision.datasets.ImageFolder
    """

    # override the __getitem__ method. this is the method that dataloader calls
    def __getitem__(self, index):
        # this is what ImageFolder normally returns 
        original_tuple = super(ImageFolderWithPaths, self).__getitem__(index)
        # the image file path
        path = self.imgs[index][0]
        # make a new tuple that includes original and the path
        tuple_with_path = (original_tuple + (path,))
        return tuple_with_path

和示例用法：

data_dir = "your/data_dir/here"
dataset = ImageFolderWithPaths(data_dir) # our custom dataset
dataloader = torch.utils.DataLoader(dataset)

# iterate over data
for inputs, labels, paths in dataloader:
    # use the above variables freely
    print(inputs, labels, paths)

我的代码：

from pytorch_image_folder_with_file_paths import ImageFolderWithPaths

folder_dataset_test = dset.ImageFolder(root=Config.testing_dir)
siamese_dataset = SiameseNetworkDataset(imageFolderDataset=folder_dataset_test,
                                        transform=transforms.Compose([transforms.Resize((100,100)),
                                                                      transforms.ToTensor()
                                                                      ])
                                       ,should_invert=False)

test_dataloader = DataLoader(siamese_dataset,num_workers=6,batch_size=1,shuffle=True)

dataiter = iter(test_dataloader)
x0,_,_ = next(dataiter)

for i in range(10):
    _,x1,label2 = next(dataiter)

    concatenated = torch.cat((x0,x1),0)

    output1,output2 = net(Variable(x0).cuda(),Variable(x1).cuda())
    euclidean_distance = F.pairwise_distance(output1, output2)
    imshow(torchvision.utils.make_grid(concatenated),'Dissimilarity: {:.2f}'.format(euclidean_distance.item()))

for inputs, labels, paths in test_dataloader:
    print(inputs, labels, paths)

我得到了具有不同分数的配对图像，但我没有得到路径；我明白了

tensor([[[[0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.],
          ...,
          [0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.]]]]) tensor([[[[0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.],
          [0., 0., 0.,  ..., 0., 0., 0.],
          ...,

...ETC。

谢谢

4

1 回答 1

1

谢谢你Anubhav Singh帮我整理。

这有效：

from pytorch_image_folder_with_file_paths import ImageFolderWithPaths

folder_dataset_test = ImageFolderWithPaths(root=Config.testing_dir)
siamese_dataset = SiameseNetworkDataset(imageFolderDataset=folder_dataset_test,
                                        transform=transforms.Compose([transforms.Resize((100,100)),
                                                                      transforms.ToTensor()
                                                                      ])
                                       ,should_invert=False)

test_dataloader = DataLoader(siamese_dataset,num_workers=6,batch_size=1,shuffle=True)

dataiter = iter(test_dataloader)
x0,_,_ = next(dataiter)

for i in range(10):
    _,x1,label2 = next(dataiter)

    concatenated = torch.cat((x0,x1),0)

    output1,output2 = net(Variable(x0).cuda(),Variable(x1).cuda())
    euclidean_distance = F.pairwise_distance(output1, output2)
    imshow(torchvision.utils.make_grid(concatenated),'Dissimilarity: {:.2f}'.format(euclidean_distance.item()))

for paths in folder_dataset_test:
    # use the above variables freely
    print(paths)

顺便说一句，我在 Google Colab 工作，它不允许我直接编辑文件，所以对于数据加载器，我制作了一个新单元格并用来%%writefile将其放入我的笔记本中：

%%writefile pytorch_image_folder_with_file_paths.py

import torch
import torchvision.datasets as dset

class ImageFolderWithPaths(dset.ImageFolder):
    """Custom dataset that includes image file paths. Extends
    torchvision.datasets.ImageFolder
    """

    # override the __getitem__ method. this is the method that dataloader calls
    def __getitem__(self, index):
        # this is what ImageFolder normally returns 
        original_tuple = super(ImageFolderWithPaths, self).__getitem__(index)
        # the image file path
        path = self.imgs[index][0]
        # make a new tuple that includes original and the path
        tuple_with_path = (original_tuple + (path,))
        return tuple_with_path
于 2019-07-10T16:05:36.967 回答