google-research / bert

Watch 940
Star 23.1k
Fork 6.5k

Code
Issues 631
Pull requests 72
Actions
Projects 0
Security
Insights

Code Issues 631 Pull requests 72 Projects 0 Actions Security Pulse

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Pick a username

Email Address

Password

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

631 Open 299 Closed

Author

Filter by author

Label

Filter by label

Use alt + click/return to exclude labels.

Projects

Filter by project

Milestones

Filter by milestone

Assignee

Filter by who’s assigned

Sort

Sort by

Newest Oldest Most commented Least commented Recently updated Least recently updated

Most reactions

tokenization of well formed structures in language

#1090 opened May 23, 2020 by dhruvsakalley

module 'tensorflow_core._api.v2.train' has no attribute 'Saver'

#1087 opened May 18, 2020 by adarshrana205

run run_classifier there's an Error!

#1086 opened May 18, 2020 by richiesui

extract_features sentence embedding BERT

#1085 opened May 18, 2020 by efabb95

Sentence embeddings

#1084 opened May 14, 2020 by efabb95

Adding custom domain words and abbreviations to vocab.txt

#1083 opened May 13, 2020 by saklanipankaj

How to choose num_train_step in run_pretraining.py ?

#1081 opened May 5, 2020 by max-yue

BERT is capable to predict phrasel keyword in NER ?

#1080 opened May 4, 2020 by Swty13

deploy on serverless architecture

#1079 opened May 3, 2020 by flieks

Do_predict does not make predictions for all instances in the test.tsv

#1078 opened May 2, 2020 by Mahhos

How much GPU memory shall I have if I want to fine-tuning BERT-large?

#1075 opened Apr 28, 2020 by 14H034160212

Are adam weights and variances necessary to continue pretraining?

#1074 opened Apr 27, 2020 by pretidav

Error extract features trained model

#1073 opened Apr 26, 2020 by efabb95

pretraining BERT CASED model gives lower accuracy than UNCASED

#1069 opened Apr 21, 2020 by yzhang123

Pretrain without Next Sentence Prediction Task

#1068 opened Apr 21, 2020 by muhammadfahid51

Pooled output is different from first vector of sequence output

#1067 opened Apr 21, 2020 by tqdo

BERT-Tiny,BERT-Mini,BERT-Small,BERT-Medium - TF 2.0 checkpoints

#1066 opened Apr 20, 2020 by 17patelumang

What's the difference between use_one_hot_embeddings and tf.gather in embedding_lookup

#1065 opened Apr 20, 2020 by lqj679ssn

Why we get last 4 layers while residual connection transfer useful knowledge to the subsequent layers?

#1064 opened Apr 19, 2020 by pbabvey

how to understand the segmention embeddings

#1063 opened Apr 19, 2020 by Pacerzhujiang0112

what is the different between the model in gs and tensorflow.hub

#1062 opened Apr 18, 2020 by bastia1989

"logits must be 2-dimensional" error on TF 1.9

#1061 opened Apr 17, 2020 by alpsholic

How is this counted? --> "3.3 billion word corpus"

#1060 opened Apr 16, 2020 by leejason

How to get the embedded tabel size after pre-training

#1059 opened Apr 15, 2020 by memani1

How many epoch do we need when pretraining bert?

#1058 opened Apr 15, 2020 by melody2cmy

Previous 1 2 3 4 5 … 25 26 Next

Previous Next

ProTip! Find all open issues with in progress development work with linked:pr.