ParseError:未找到元素：行1，列0

Question

我试着用Pythorch训练一个网络。该数据集包括许多jpg和xml文件中的注释（标签和边界框）。我编写了一个用于提取注释的基本数据加载器。在

class dataLoader(dataset):
def __init__(self, path, root, img_trfm=None, resize=None):
    self.filename = get_file_name(path)
    self.data = self.filename
    self.root = root
    self.resize = resize
    self.img_resize = transforms.Resize((resize, resize))
    self.img_trfm = img_trfm
    self.data_len = len(self.data)

def __getitem__(self, index):
    filename = (self.filename[index])
    objects, num_objs = get_targets(filename+'.xml')
    img_name = objects[-1]
    img = Image.open(self.root+img_name+'.jpg')
    img_trfm = self.img_trfm(img)
    #adds a dictionary for name of classes to 
    #corresponding integers 
    for i in range(num_objs-1):
        objects[i]['bndbox'] = torch.Tensor(objects[i]['bndbox'])
        objects[i]['id'] = get_class_id(objects[i]['label']) 
    return img_trfm, objects[:-1]

def __len__(self):
    return self.data_len

输出是单个图像和图像中每个对象的字典列表：

^{pr2}$

我还编写了一个基本的培训函数，用于仅使用标签id对网络进行培训：

for epoch in range(1): 
    running_loss = 0.0
    for data in trainloader:
        images, objects = data
        for k in objects:
            label = k['id']
            #label = label.type(torch.FloatTensor) 
            print(label)
            optimizer.zero_grad()
            outputs = net(images)
            loss = criterion(outputs, label)
            loss.backward()
            print(loss)
            optimizer.step()

它似乎在起作用，因为我得到了损失价值：

tensor(0.46, grad_fn=<NllLossBackward>)
tensor(0.46, grad_fn=<NllLossBackward>)
tensor(2.13, grad_fn=<NllLossBackward>)
tensor(0.45, grad_fn=<NllLossBackward>)
tensor(0.44, grad_fn=<NllLossBackward>)
tensor(1.57, grad_fn=<NllLossBackward>)
tensor(0.43, grad_fn=<NllLossBackward>)
tensor(0.43, grad_fn=<NllLossBackward>)
tensor(2.30, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
tensor(1.66, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
tensor(2.12, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
tensor(0.42, grad_fn=<NllLossBackward>)
......

但是，在这些损失值之后，我一直收到以下错误消息：

  File "/miniconda3/envs/env_PyTorch/lib/python3.7/xml/etree/ElementTree.py", line 598, in parse
    self._root = parser._parse_whole(source)

  File "<string>", line unknown
ParseError: no element found: line 1, column

如有任何建议，将不胜感激。在