Chevron Left
Fine Tune BERT for Text Classification with TensorFlow に戻る

Coursera Project Network による Fine Tune BERT for Text Classification with TensorFlow の受講者のレビューおよびフィードバック



This is a guided project on fine-tuning a Bidirectional Transformers for Language Understanding (BERT) model for text classification with TensorFlow. In this 2.5 hour long project, you will learn to preprocess and tokenize data for BERT classification, build TensorFlow input pipelines for text data with the API, and train and evaluate a fine-tuned BERT model for text classification with TensorFlow 2 and TensorFlow Hub. Prerequisites: In order to successfully complete this project, you should be competent in the Python programming language, be familiar with deep learning for Natural Language Processing (NLP), and have trained models with TensorFlow or and its Keras API. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....



The project was well explained and provided good understanding of bert for text classification. Also the quiz were good.


It would be helpful if the course was also offered outside of Google colab environment (standalone).


Fine Tune BERT for Text Classification with TensorFlow: 1 - 20 / 20 レビュー

by Anup P


Excellent course for those who already has done some research on the field.

by vibhor s


1.No video are there to explain the concepts(it has a video link which doesn't work).

2.There is no Rhyme Environment as mentioned in the description.

3.It only has a notebook which contains only the code without any explanation.

by David N


Very helpful to have it explained so patiently and thoroughly. I am not sure how one starts to really be able to practically work these deep and intricate libraries without the training wheels of all the guidance in these courses. But regardless, if would probably be prohibitively difficult without them, so I am grateful fo all the folks at Coursera that take the time to produce this material and courses.

by Yashvander B


The course is just awesome. I searched a ton of tutorials on fine tuning before landing onto this guided-project and I can't tell how blessed I feel now. The course is even better than most full TensorFlow tutorials which teach all the vague stuff that I have to omit all the time. Snehan has beautifully explained what is "just necessary" to dive into fine tuning BERT.

Thanks for the course :)

by Feng J


This is such a great course !!!! The instructor prepared the knowledge very well, and he is so good at teaching ! I have learned a lot skills about Bert model in this course ! You should not miss it. I am hoping to see more course from this instructor! Thank you so much for making such a great course !

by Vijender S


The project was well explained and provided good understanding of bert for text classification. Also the quiz were good.

by Fancy Y


It would be helpful if the course was also offered outside of Google colab environment (standalone).



Helped me cement the basic understanding on how to use BERT for my use case.

by James S


Great course. Easy to follow & straightforward explanations.

by Sitison


really nice glue to connect all the dots. Thanks so much

by Janmejay B


Need More detail explanation as its a advance NLP topic.

by Rohit L


N​eed a bit of preknowledge of bert and preprocessing

by Tiffany T


A great introduction to BERT and with TensorFlow

by Quỳnh C


the project is perfect. Thank you very much

by Vale


A complex topic explain in one day

by Rahul B


Really informative course




by Jorge H G G


I do not recommend taking this type of course, take one and pass it, however after a few days I have tried to review the material, and my surprise is that it asks me to pay again to be able to review the material. Of course coursera gives me a small discount for having already paid it previously. It is very easy to download the videos and difficult to get hold of the material, but with ingenuity it is possible. Then I recommend uploading them to YouTube and keeping them private for when they want to consult (they avoid legal problems and can share with friends), then they can request a refund.

by Yanfei C


The project is very clear and easy to follow. Would suggest providing some gmail account so that we don't have to log into the colab using our own google credentials.

by bilzard


It's good to learn how to implement BERT model with pyTorch.

Personally, I need more theoretical instructions about BERT and transformer.