llz-lian/bysjchange_polygon_rnn

毕业设计

bysjchange_polygon_rnn's Issues

about training code

The code in train.py cannot train the PolygonNet in mymodel.py. I found that this is a multi-task learning. Can you update your code? Thank you!!!

question

hello, can I ask you a question?
I always meet the problem:
it trouble me a lot

Loading completed!
Traceback (most recent call last):
File "d:/bysjchange_polygon_RNN-main/train.py", line 110, in
train(config, config['pretrained'])
File "d:/bysjchange_polygon_RNN-main/train.py", line 52, in train
for step, data in enumerate(Dataloader):#4->
File "D:\Segment\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 363, in next
data = self._next_data()
File "D:\Segment\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 403, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\Segment\envs\pytorch\lib\site-packages\torch\utils\data_utils\fetch.py", line 47, in fetch
return self.collate_fn(data)
File "D:\Segment\envs\pytorch\lib\site-packages\torch\utils\data_utils\collate.py", line 86, in default_collate
raise TypeError(default_collate_err_msg_format.format(elem_type))
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'NoneType'>

How can I solve the None Type Error?
Thank you and best wishes