我有两个文件夹。一个文件夹里有一张图片，另一个文件夹里有另一张图片。我需要比较这两张图片并找出它们的差异，但代码是从随机文件夹中选择的图片。

class InferenceSiameseNetworkDataset(Dataset):        def __init__(self,imageFolderDataset,transform=None,should_invert=True):        self.imageFolderDataset = imageFolderDataset            self.transform = transform        self.should_invert = should_invert            def __getitem__(self,index):        img0_tuple = random.choice(self.imageFolderDataset.imgs)        img1_tuple = random.choice(self.imageFolderDataset.imgs)        #we need to make sure approx 50% of images are in the same class        should_get_same_class = random.randint(0,1)         if should_get_same_class:            while True:                #keep looping till the same class image is found                img1_tuple = random.choice(self.imageFolderDataset.imgs)                 if img0_tuple[1]==img1_tuple[1]:                    break        else:            while True:                #keep looping till a different class image is found                                img1_tuple = random.choice(self.imageFolderDataset.imgs)                 if img0_tuple[1] !=img1_tuple[1]:                    break        img0 = Image.open(img0_tuple[0])        img1 = Image.open(img1_tuple[0])        img0 = img0.convert("L")        img1 = img1.convert("L")                if self.should_invert:            img0 = PIL.ImageOps.invert(img0)            img1 = PIL.ImageOps.invert(img1)        if self.transform is not None:            img0 = self.transform(img0)            img1 = self.transform(img1)                return img0, img1 , torch.from_numpy(np.array([int(img1_tuple[1]!=img0_tuple[1])],dtype=np.float32))        def __len__(self):        return len(self.imageFolderDataset.imgs)

我从GitHub上获取了这段代码，当我尝试比较两张图片的差异时，它会随机选择图片。输入文件夹有两个，一个图片应该在一个文件夹中，另一个图片应该在另一个文件夹中。当我尝试测试时，有时它会在同一个图片上进行测试，我的意思是它没有检查另一个文件夹中的另一张图片。

testing_dir1 = '/content/drive/My Drive/Signature Dissimilarity/Forged_Signature_Verification/processed_dataset/training1/'folder_dataset_test = dset.ImageFolder(root=testing_dir1)siamese_dataset = InferenceSiameseNetworkDataset(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=False)dataiter = iter(test_dataloader)x0,_,_ = next(dataiter)for i in range(2):  _,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()))  dis = 'Dissimilarity: {:.2f}'.format(euclidean_distance.item())  dis1 = dis  dis1 = dis1.replace("Dissimilarity:", "").replace(" ", "")  print(dis)  if float(dis1) < 0.5:    print("It's Same Signature")  else:    print("It's Forged Signature")

回答：

只需在自定义数据集类InferenceSiameseNetworkDataset的__getitem__函数中将should_get_same_class设为0，你就可以确保两张图片属于不同的类/文件夹。

其次，你不应该连接可能不满足你条件的两个批次的样本。你应该在循环范围内使用x0,x1,label2 = next(dataiter)，然后进行连接操作。