KeyError: Caught KeyError in DataLoader worker process 0. KeyError: 'load_db_to_memory'

[pikaduo001]

)
(act): LeakyReLU(negative_slope=0.2, inplace=True)
)
(1): Conv1d(128, 204, kernel_size=(1,), stride=(1,))
)
)
| model Trainable Parameters: 0.797M
Sanity Val: 0%| | 0/5 [00:02<?, ?step/s]
Traceback (most recent call last):
File "D:\Workspace\Digital_Human\GeneFace\tasks\run.py", line 19, in
run_task()
File "D:\Workspace\Digital_Human\GeneFace\tasks\run.py", line 14, in run_task
task_cls.start()
File "D:\Workspace\Digital_Human\GeneFace\utils\commons\base_task.py", line 251, in start
trainer.fit(cls)
File "D:\Workspace\Digital_Human\GeneFace\utils\commons\trainer.py", line 126, in fit
self.run_single_process(self.task)
File "D:\Workspace\Digital_Human\GeneFace\utils\commons\trainer.py", line 190, in run_single_process
self.train()
File "D:\Workspace\Digital_Human\GeneFace\utils\commons\trainer.py", line 265, in train
self.evaluate(self.task, False, 'Sanity Val', max_batches=self.num_sanity_val_steps)
File "D:\Workspace\Digital_Human\GeneFace\utils\commons\trainer.py", line 227, in evaluate
for batch_idx, batch in enumerate(pbar):
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\tqdm\std.py", line 1181, in iter
for obj in iterable:
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data\dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data\dataloader.py", line 1371, in _process_data
data.reraise()
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch_utils.py", line 644, in reraise
raise exception
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\ProgramData\anaconda3\envs\geneface\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\Workspace\Digital_Human\GeneFace\tasks\postnet\dataset_utils.py", line 80, in getitem
sample = self.audio2motion_ds[idx]
File "D:\Workspace\Digital_Human\GeneFace\tasks\audio2motion\dataset_utils\lrs3_dataset.py", line 191, in getitem
if hparams['load_db_to_memory']:
KeyError: 'load_db_to_memory'

[W ..\torch\csrc\CudaIPCTypes.cpp:15] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]

(geneface) D:\Workspace\Digital_Human\GeneFace> 步骤3. 训练PostNet模型报错，如何处理？