demo-chinese-text-binary-classification-with-bert's People
Forkers
nanhaishun zhangjiekui babyzpj lalala215 scottishfold007 boluoyu hungita felixgithub2017 haisimao sherryguo8023 yingluofeihua ly-cunji iamgy yuzhiw mingjiewang0606 plodded baopu00 aiedward paul0m vesauza amydoulaohu gptcod n2lzxcstars anigi98932 yaoleihxr raymondci pantingpanting lycreative zhiyongliu1114 tandy017 yuchia0518 gm19900510 moshilangzi zixuedanxin xichunling tslnihaogit mahaoyang pandongning lucassocct mejihero jiaxiangbu 171860596 huamulou colinsongf xpp404 wushicanasl reejuly wondergcj awesome-archive ares5221 glimmser hellomaxwell szxiaosheng dj123jary df14jsj117 glaceage linzhang92 wzf9 leeyongheng mindsky-space cc1019054695 helenzzzzzz 15657318057 yxj-1111 baimax321 gardendream zhuyaolin loveglory someonehereany alfonsocheng1025 lxyazi jiwangduan lebronhe boyu29 candy77721 shihanyang zhangxuemiao xmglover wisd0mbalala zoey-wangzw allen-lzh tingnlp rvlis tu-dan lydia1990321-1 sense1011 liuyunwu luoluojinjiner jasper-huang-0wo yb-huang jungyitsai cchengjie gitbub1992 eathoublu nehasingh2710 hwf87 chiwenheng xukai98 nkzhangheng manman-zcdemo-chinese-text-binary-classification-with-bert's Issues
AttributeError: module 'tensorflow' has no attribute 'Session'
Seems tf2.x don't have tf.Session()
大文本可以用bert来处理吗
我的文本有将近2千个字来做多标签。用bert实际吗
自定义字典
你好,请问如何载入自定义的字典呢?我仅仅想将字符串转换为数字,有自己的字典,但是应该如何载入呢
UnparsedFlagAccessError: Trying to access flag --preserve_unused_tokens before flags were parsed.
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
INFO:tensorflow:Writing example 0 of 1799
INFO:tensorflow:Writing example 0 of 1799
UnparsedFlagAccessError Traceback (most recent call last)
in ()
----> 1 result, estimator = run_on_dfs(train, test, **myparam)
7 frames
/usr/local/lib/python3.6/dist-packages/absl/flags/_flagvalues.py in getattr(self, name)
489 # get too much noise.
490 logging.error(error_message)
--> 491 raise _exceptions.UnparsedFlagAccessError(error_message)
492
493 def setattr(self, name, value):
UnparsedFlagAccessError: Trying to access flag --preserve_unused_tokens before flags were parsed.
请问为什么会出现这个问题啊
是否可以使用pytorch实现的bert进行分类呢
請問如何獲得embedding結果?
請問該如何修改code已獲得bert對於文字的embedding結果?
请教一下
运行最后一步result, estimator的时候出现URLError: <urlopen error [Errno 101] Network is unreachable>,请问怎么解决呀
請教一下,如果想讓輸出為機率值該怎麼改
請教一下,如果想看到預測之機率值(就是用softmax後的log_probs)該怎麼改,謝謝!
在小规模数据集上过拟合
你好,我在一个小规模上数据集上使用bert二分类,出现了严重的过拟合,有没有什么好的解决办法
module 'tensorflow.python.framework.op_def_registry' has no attribute 'register_op_list'
作者您好,作为一个小白,xiang wen xia这个错误怎么解决.一个上午了,太惨了
ModuleNotFoundError: No module named 'tensorflow.contrib'
跑脚本的时候一开始就报错,似乎是tensorflow2下面不支持bert 的tensorflow.contrib了,可以问下有人知道怎么解决吗?
关于模型保存,请教一下。
它预测标签值的时候会自动加载已经保存的模型吗?我使用相同的数据进行预测,但是获得的值不一样。
UnparsedFlagAccessError: Trying to access flag --preserve_unused_tokens before flags were parsed.
/usr/local/lib/python3.7/dist-packages/absl/flags/_flagvalues.py in getattr(self, name)
477 else:
478 raise _exceptions.UnparsedFlagAccessError(
--> 479 'Trying to access flag --%s before flags were parsed.' % name)
480
481 def setattr(self, name, value):
UnparsedFlagAccessError: Trying to access flag --preserve_unused_tokens before flags were parsed.
how to solve this problem!
想請教bert Chinese 如何設定GPU
謝謝閣下寶貴的分享, 但google colab有兩個問題,
-
Ram用量不足, 我有近1百萬條records, bert-chinese 行了1分鍾, Ram用量已盡。
唯今之計, 我花錢在paperspace gradient上運行, 暫未有結果。 -
在閣下的 demo-chinese-text-binary-classification-with-bert 內, 如何設定GPU使用? 可否賜教
謝謝
请问出现module 'tensorflow._api.v2.train' has no attribute 'Optimizer'怎么解决?
请问出现module 'tensorflow._api.v2.train' has no attribute 'Optimizer'怎么解决?
请问我想输出具体分类结果我应该怎么修改
我想要输出具体的测试分类的结果,比如“不错,宝宝喜欢”预测结果为“1”
请问如何使用非官方的预训练模型
您好!感谢你的分享。我想加载非tensorflow-hub的模型该怎么做呢?
如:https://github.com/ymcui/Chinese-BERT-wwm下的BERT-www
https://github.com/brightmart/albert_zh下的albert
这里下载的模型都跟官方模型格式不一样。想请问一下该怎么使用呢?
当我用hub.Moudle去加载本地文件的时候报错,请教一下
E:\Anaconda\lib\site-packages\tensorflow_hub\registry.py in call(self, args, **kwargs)
43 raise RuntimeError(
44 "Missing implementation that supports: %s(%r, **%r)" % (
---> 45 self._name, args, kwargs))
46
47
RuntimeError: Missing implementation that supports: loader(*('./chinese_L-12_H-768_A-12',), **{})
我去官网上去看了 说是支持加载本地模型,去git上看源码也是发现可以的,所以报这个错不知道怎么改?上不了外网,所以没有去试url,谢谢
请教一下进行中文文本多类分类需要修改哪些参数呢?
如题
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.