RuntimeError: expected predicate to be bool, got torch.uint8

[githubjixin]

您好作者，请教一下大佬，我在运行main.py时
遇到的这个uint-8的问题，整个程序都可以运行，这个对整体效果会有影响吗，请您帮忙看一下

[2023-08-31 10:45:35,911] torch._dynamo.convert_frame: [INFO] converting frame raised error, suppressing error
[2023-08-31 10:45:35,971] torch._dynamo.symbolic_convert: [INFO] Step 1: torchdynamo start tracing _compute_normalizer
[2023-08-31 10:45:35,999] torch._dynamo.convert_frame: [ERROR] WON'T CONVERT _compute_normalizer /Users/mac/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torchcrf/init.py line 208
due to:
Traceback (most recent call last):
File "/Users/mac/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torch/_prims_common/init.py", line 1563, in check
raise exc_type(s())
RuntimeError: expected predicate to be bool, got torch.uint8

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/Users/mac/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torch/_dynamo/utils.py", line 1206, in run_node
raise RuntimeError(
RuntimeError: Failed running call_function <built-in method where of type object at 0x12f69d850>(*(FakeTensor(FakeTensor(..., device='meta', size=(32, 1), dtype=torch.uint8), cpu), FakeTensor(FakeTensor(..., device='meta', size=(32, 105), grad_fn=), cpu), FakeTensor(FakeTensor(..., device='meta', size=(32, 105), grad_fn=), cpu)), **{}):
expected predicate to be bool, got torch.uint8
(scroll up for backtrace)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/Users/mac/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torch/_dynamo/utils.py", line 1173, in get_fake_value
raise TorchRuntimeError() from e
torch._dynamo.exc.TorchRuntimeError:

from user code:
File "/Users/mac/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torchcrf/init.py", line 249, in _compute_normalizer
score = torch.where(mask[i].unsqueeze(1), next_score, score)

Set torch._dynamo.config.verbose=True for more information

[taishan1994]

没有报错导致程序中断就应该没啥影响。