使用DataLoader报错AttributeError: 'int' object has no attribute 'numel'

　　在跑这段代码的时候报错

concat_dataset = ConcatDataset([train_dataset, new_set])
train_data = DataLoader(concat_dataset, batch_size=batch_size, shuffle=True, num_workers=2, pin_memory=True)
for data, y in train_data:
  print(data, y）

Original Traceback (most recent call last): 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
　　 data = fetcher.fetch(index) 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch 
　　return self.collate_fn(data) 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 84, in default_collate 
　　return [default_collate(samples) for samples in transposed] 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 84, in <listcomp> 
　　return [default_collate(samples) for samples in transposed] 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 53, in default_collate 
　　numel = sum([x.numel() for x in batch]) 
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 53, in <listcomp> 
　　numel = sum([x.numel() for x in batch]) 
AttributeError: 'int' object has no attribute 'numel'

　　使用了ConcatDataset合并两个dataset后，进行数据加载的时候报错了，主要原因是合并的两个dataset返回的数据类型不一致，遍历两个dataset可以看到一个返回的是'int'，一个返回的是'tensor'。

　　    

 

　　 将两个dataset返回的结果改成一致的，就可以解决问题了。