wzzzd/lm_ner_span

Issues

• data/CNER/里的label为空

  #8 opened 2 years ago by CRonaldo1997
  0

• Traceback (most recent call last): File "run.py", line 46, in <module> train_loader = dm.get_dataset(data_type='train') File "/user-data/lm_ner_span-main/DataManager.py", line 34, in get_dataset dataloader = self.data_process(file) File "/user-data/lm_ner_span-main/DataManager.py", line 68, in data_process sampler = RandomSampler(tokenized_datasets) if not torch.cuda.device_count() > 1 else DistributedSampler(tokenized_datasets) File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/sampler.py", line 103, in __init__ raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but got num_samples=0 请问这个报错怎么解决啊 好像是dataloader出错了 但是按照网上的解决办法将参数shuffle设置为FALSE还是没办法解决 请问大佬有什么解决办法吗

  #3 opened 2 years ago by 20214021016
  2

• 求解！！！

  #7 opened 2 years ago by khazic
  0

• 请问将序列标注任务转化为预测首尾指针的任务具体在哪儿体现的，是bert编码过程中只对首尾部分进行编码，其他部分mask掉吗？

  #6 opened 2 years ago by 20214021016
  1

• DataManager.py中的DataManager:padding()里面的实现有点问题

  #5 opened 2 years ago by erichuazhou
  0

• 对抗学习参数问题

  #4 opened 2 years ago by ZZQ908268856
  4

• ValueError: num_samples should be a positive integer value, but got num_samples=0 请问此句报错怎么解决啊

  #1 opened 2 years ago by 20214021016
  0

• Traceback (most recent call last): File "run.py", line 46, in <module> train_loader = dm.get_dataset(data_type='train') File "/user-data/lm_ner_span-main/DataManager.py", line 34, in get_dataset dataloader = self.data_process(file) File "/user-data/lm_ner_span-main/DataManager.py", line 68, in data_process sampler = RandomSampler(tokenized_datasets) if not torch.cuda.device_count() > 1 else DistributedSampler(tokenized_datasets) File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/sampler.py", line 103, in __init__ raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but got num_samples=0

  #2 opened 2 years ago by 20214021016
  0