AttributeError: 'NoneType' object has no attribute 'tokenize'

[wss-xm]

No description provided.

[wss-xm]

tokens = self.tokenizer.tokenize(line.strip())

AttributeError: 'NoneType' object has no attribute 'tokenize'

[tongchangD]

How did you solve the problem

[wss-xm]

Sorry, I don't solve the problem At 2020-08-04 14:05:48, "tongchangD" <[email protected]> wrote: How did you solve the problem — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[tongchangD]

Sorry, I don't solve the problem At 2020-08-04 14:05:48, "tongchangD" [email protected] wrote: How did you solve the problem — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

i change the tokenize，you can see in
from pytorch_pretrained_bert import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('./dataset/bert-base-chinese')

[yolanda182]

Sorry, I don't solve the problem At 2020-08-04 14:05:48, "tongchangD" [email protected] wrote: How did you solve the problem — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

i change the tokenize，you can see in
from pytorch_pretrained_bert import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('./dataset/bert-base-chinese')

Could you please tell me where you change it?

[tongchangD]

Sorry, I don't solve the problem At 2020-08-04 14:05:48, "tongchangD" [email protected] wrote: How did you solve the problem — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

i change the tokenize，you can see in
from pytorch_pretrained_bert import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('./dataset/bert-base-chinese')

Could you please tell me where you change it?

I modified it on the company computer