blocks|key|1280788|text|我找到了它：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1280789|!pip+install+bert-tensorflow|code-block|syntax|javascript|1280790|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

I found it:

<pre><code>!pip install bert-tensorflow
</code></pre>

blocks|key|1363483|text|安装：pip+install+bert-for-tf2|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1363484|然后进口，|1363485|from+bert+import+bert_tokenization++BertTokenizer+=+bert_tokenization.FullTokenizer|1363486|entityMap^0|3|O|0|0|0|2B|0^^$0|@$1|2|3|4|5|6|7|L|8|@$9|M|A|N|B|C]]|D|@]|E|$]]|$1|F|3|G|5|6|7|O|8|@]|D|@]|E|$]]|$1|H|3|I|5|6|7|P|8|@$9|Q|A|R|B|C]]|D|@]|E|$]]|$1|J|3|-4|5|6|7|S|8|@]|D|@]|E|$]]]|K|$]]

install :
<code>pip install bert-for-tf2</code>

then import,

<code>from bert import bert_tokenization
 BertTokenizer = bert_tokenization.FullTokenizer</code>

blocks|key|3560347|text|对于使用TensorFlow+2.0和bert+For+-TF2库遇到这个问题的人，我发现在使用pip3安装后丢失了一些文件。我在这里发布了我的解决方案：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|3560348|https://github.com/google-research/bert/issues/638#issuecomment-592488730|offset|length|3560349|entityMap|0|LINK|mutability|MUTABLE|url^0|0|0|21|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|N|8|@]|9|@$D|O|E|P|1|Q]]|A|$]]|$1|F|3|-4|5|6|7|R|8|@]|9|@]|A|$]]]|G|$H|$5|I|J|K|A|$L|C]]]]

For anyone experiencing this problem with TensorFlow 2.0 and the bert-for-tf2 library, I found out that I was missing some files after using pip3 install. I've posted my solution here:

<a href="https://github.com/google-research/bert/issues/638#issuecomment-592488730" rel="nofollow noreferrer">https://github.com/google-research/bert/issues/638#issuecomment-592488730</a>

blocks|key|1363530|text|或者您可以使用早期版本的BERT来避免进一步的并发症(至少目前是这样)。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1363531|!pip+install+tensorflow-gpu==1.15.0
!pip+install+bert-tensorflow
from+sklearn.model_selection+import+train_test_split
import+pandas+as+pd
import+tensorflow+as+tf
import+tensorflow_hub+as+hub
from+datetime+import+datetime
import+bert
from+bert+import+run_classifier
from+bert+import+optimization
from+bert+import+tokenization|code-block|syntax|javascript|1363532|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

or you may use previous version of BERT to avoid further complications (Atleast for now)

<pre><code>!pip install tensorflow-gpu==1.15.0
!pip install bert-tensorflow
from sklearn.model_selection import train_test_split
import pandas as pd
import tensorflow as tf
import tensorflow_hub as hub
from datetime import datetime
import bert
from bert import run_classifier
from bert import optimization
from bert import tokenization
</code></pre>

blocks|key|1363546|text|在tf1中：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1363547|!pip+install+bert-tokenizer|code-block|syntax|javascript|1363548|import+bert_tokenizer+as+tokenization

tokenization.tokenizer.FullTokenizer|1363549|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|K|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|L|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|D|7|M|8|@]|9|@]|A|$E|F]]|$1|I|3|-4|5|6|7|N|8|@]|9|@]|A|$]]]|J|$]]

In tf1:
<pre><code>!pip install bert-tokenizer
</code></pre>
<pre><code>import bert_tokenizer as tokenization

tokenization.tokenizer.FullTokenizer
</code></pre>

blocks|key|1280957|text|我可以通过使用pip3和pip卸载和安装来修复它。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1280958|!pip3++uninstall+-y+bert-tensorflow+
!pip++uninstall+-y+bert-tensorflow

!pip3++install+bert-tensorflow+
!pip+install+bert-tensorflow|code-block|syntax|javascript|1280959|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

I could fix it by uninstalling and installing using both pip3 and pip.
<pre><code>!pip3 uninstall -y bert-tensorflow 
!pip uninstall -y bert-tensorflow

!pip3 install bert-tensorflow 
!pip install bert-tensorflow
</code></pre>

blocks|key|1363463|text|这对我起了作用：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1363464|!pip+install+bert-tokenizer|code-block|syntax|javascript|1363465|使用：|1363466|import+bert_tokenizer+as+tokenizer|1363467|import+bert_tokenization+as+tokenization+！|offset|length|style|BOLD|CODE|1363468|entityMap^0|0|0|0|0|0|14|15|1|0|14|0^^$0|@$1|2|3|4|5|6|7|T|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|U|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|V|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|W|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|X|8|@$M|Y|N|Z|O|P]|$M|10|N|11|O|P]|$M|12|N|13|O|Q]]|9|@]|A|$]]|$1|R|3|-4|5|6|7|14|8|@]|9|@]|A|$]]]|S|$]]

This worked for me:

<pre><code>!pip install bert-tokenizer
</code></pre>

to use: 

<pre><code>import bert_tokenizer as tokenizer
</code></pre>

<hr>

NOT <code>import bert_tokenization as tokenization</code> !!!

blocks|key|1280961|text|你可以试试这个：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1280962|!pip+install+bert-tensorflow

!pip+install++--upgrade+bert

!pip+install+tokenization


from+bert+import+tokenization++
from+**bert.tokenization.bert_tokenization**+import+**FullTokenizer**+


tokenizer+=+FullTokenizer(vocab_file=vocab_file,+do_lower_case=do_lower_case)|code-block|syntax|javascript|1280963|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

You might try this:
<pre><code>!pip install bert-tensorflow

!pip install --upgrade bert

!pip install tokenization


from bert import tokenization 
from **bert.tokenization.bert_tokenization** import **FullTokenizer** 


tokenizer = FullTokenizer(vocab_file=vocab_file, do_lower_case=do_lower_case)
</code></pre>

I am using Google Colab and the following import doesn't work somehow:

<pre><code>from bert.tokenization import FullTokenizer
</code></pre>

I am getting this error:

<pre><code>ModuleNotFoundError: No module named 'bert.tokenization'
</code></pre>

I tried to install bert by running the following command:

<pre><code>!pip install --upgrade bert
</code></pre>

Any idea how to resolve this error?

Can't import bert.tokenization

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

我使用的是Google，下面的导入不知何故不起作用：from bert.tokenization import FullTokenizer我得到了这个错误：ModuleNotFoundError: No module named 'bert.tokenization'我试图通过运行以下命令来安装bert：!pip install  --upgrade bert知道如何解决这个错误吗？

问无法导入bert.tokenization
EN

回答 8

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问无法导入bert.tokenizationEN

回答 8

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问无法导入bert.tokenization
EN