训练到一半出现的报错 RuntimeError: torch.cat(): expected a non-empty list of Tensors

[laishujie]

Traceback (most recent call last):
File "kantts/bin/train_sambert.py", line 224, in train
trainer.train()
File "/home/l/project/KAN-TTS_/kantts/train/trainer.py", line 210, in train
self.train_epoch()
File "/home/l/project/KAN-TTS_/kantts/train/trainer.py", line 223, in train_epoch
self.check_eval_interval()
File "/home/l/project/KAN-TTS_/kantts/train/trainer.py", line 200, in check_eval_interval
self.eval_epoch()
File "/home/l/project/KAN-TTS_/kantts/train/trainer.py", line 270, in eval_epoch
self.genearete_and_save_intermediate_result(batch)
File "/home/l/miniconda3/envs/modelscope/lib/python3.8/site-packages/torch/utils/contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/l/project/KAN-TTS/kantts/train/trainer.py", line 739, in genearete_and_save_intermediate_result
res = self.model["KanTtsSAMBERT"](
File "/home/l/miniconda3/envs/modelscope/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in call_impl
return forward_call(*args, **kwargs)
File "/home/l/project/KAN-TTS/kantts/models/sambert/kantts_sambert.py", line 995, in forward
dec_outputs, pnca_x_attn_lst, pnca_h_attn_lst = self.mel_decoder(
File "/home/l/miniconda3/envs/modelscope/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in call_impl
return forward_call(*args, **kwargs)
File "/home/l/project/KAN-TTS/kantts/models/sambert/kantts_sambert.py", line 603, in forward
dec_output = torch.cat(dec_output, dim=1)
RuntimeError: torch.cat(): expected a non-empty list of Tensors