Pytorch群组计数CRSNet“无法打开对象（对象不存在）”

Question

这是一个与pytorch CRSNet人群计数培训相关的问题。 运行train.py时，会发生此错误块。有人能解决这个问题或说出原因吗

(pytorch) C:\Users\pcp25\Downloads\PETS2009_copy>python train.py part_A_train.json part_A_val.json 0 0
epoch 0, processed 0 samples, lr 0.0000001000
Epoch: [0][0/1200]      Time 1.633 (1.633)      Data 0.043 (0.043)      Loss 28.0382 (28.0382)
Epoch: [0][30/1200]     Time 0.537 (0.561)      Data 0.032 (0.029)      Loss 22.3519 (514.1272)
Epoch: [0][60/1200]     Time 0.633 (0.535)      Data 0.030 (0.027)      Loss 173.2239 (516.8844)
Traceback (most recent call last):
  File "train.py", line 226, in <module>
    main()
  File "train.py", line 91, in main
    train(train_list, model, criterion, optimizer, epoch)
  File "train.py", line 129, in train
    for i, (img, target) in enumerate(train_loader):
  File "C:\Users\pcp25\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 435, in __next__
    data = self._next_data()
  File "C:\Users\pcp25\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 475, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "C:\Users\pcp25\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\Users\pcp25\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\Users\pcp25\Downloads\PETS2009_copy\dataset.py", line 35, in __getitem__
    img, target = load_data(img_path, self.train)
  File "C:\Users\pcp25\Downloads\PETS2009_copy\image.py", line 13, in load_data
    target = np.asarray(gt_file['density'])
  File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "C:\Users\pcp25\anaconda3\envs\pytorch\lib\site-packages\h5py\_hl\group.py", line 264, in __getitem__
    oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
  File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py\h5o.pyx", line 190, in h5py.h5o.open
KeyError: "Unable to open object (object 'density' doesn't exist)"