这个错误的解决方法在网上查不到

----------- Configuration Arguments -----------
batch_size: 8
checkpoints: checkpoints
class_num: 3040
device: GPU
frame_dim: 80
hidden_dim: 1024
infer_models:
init_model_path: None
learning_rate: 6.4e-05
mean_var: data/global_mean_var
minimum_batch_size: 1
parallel: True
pass_num: 100
print_per_batches: 100
proj_dim: 512
stacked_num: 5
train_feature_lst: data/train_feature.lst
train_label_lst: data/train_label.lst
val_feature_lst: data/val_feature.lst
val_label_lst: data/val_label.lst
------------------------------------------------
....................................................................................................Traceback (most recent call last):
File "../../train.py", line 292, in
train(args)
File "../../train.py", line 254, in train
(batch_id, lodtensor_to_ndarray(outs[0])[0],
File "/home/nemo/models/fluid/DeepASR/data_utils/util.py", line 31, in lodtensor_to_ndarray
dims = lod_tensor._get_dims()
AttributeError: 'paddle.fluid.core.LoDTensor' object has no attribute '_get_dims'