Deploy with FastAPI | | Sentiment Analysis with BERT using huggingface, PyTorch and Python Tutorial

Подписаться 25 тыс.

Просмотров 15 тыс.

50% 1

🗓️ 1:1 Consultation Session With Me: calendly.com/venelin-valkov/c...
📖 Get SH*T Done with PyTorch Book: bit.ly/gtd-with-pytorch
🔔 Subscribe: bit.ly/venelin-subscribe
📔 Complete tutorial + notebook: www.curiousily.com/posts/depl...
🔣 GitHub: github.com/curiousily/Getting...
Learn how to deploy a pre-trained BERT model as a REST API using FastAPI and Uvicorn
📖 Read Hacker's Guide to Machine Learning with Python Book: bit.ly/Hackers-Guide-to-Machin...
Full project on GitHub: github.com/curiousily/Deploy-...
⭐️ Tutorial Contents ⭐️
(00:00) Demo of the REST API
(02:20) Initialize a new project with pyenv and pipenv
(07:55) Create a stubbed API response
(17:30) Add the pre-trained BERT model to our project
(19:35) Reacting to a 4.5 (on the Richter scale) earthquake 🙀
(30:05) Integrate our model predictions in the REST API
#BERT #RestAPI #FastAPI #Deployment #ML #MachineLearning #Huggingface #Transformer #PyTorch #TransferLearning #SentimentAnalysis #NLP #FineTuning #DeepLearning

Наука

Опубликовано:

1 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 30

@bankingitaspirant1405 4 года назад

I'm glad to have found this channel. I am new to this stuff, but I am learning quickly. Your PyTorch book is awesome! It brought me here. It is the reason I googled your name and found this channel. Thank you man, you are a great help for new aspirants like me.

@shreyanambiar5073 2 года назад

I love this channel so much! keep up the good work :)

@venkatesanr9455 4 года назад

Waiting as usual it is going to be highly informative

@shaheerzaman620 4 года назад

Fantastic! Smooth and Easy!

@buithanhlam3726 3 года назад

Great! This is exactly what I'm looking for!

@fuat7775 4 года назад

Awesome content, thank you!

@evandrojosedossantosdiniz3046 2 года назад

Thanks! Fantastic!

@BerkayBerkman 4 года назад

Venelin, you made my day with your cool reaction to the earthquake :D :D

@MO-xi1kv 4 года назад

ahah same had to have a rewatch!

@sudharsan4040 4 года назад

Thanks for the awesome video. Can't we using hugging face pipelines for inference rather so much code? Could you please share your suggestions on inference with a custom NER model.

@every_instant 4 года назад

Thanks for the vids. How do we output attentions score for each of the user input word?

@mateusfmf994 Год назад

Thanks for the video! how can i do this for a model with four labels in the predict data ( I'm trying but I didn't succeed)

@arronslacey 3 года назад

Hi - the pretrained model link no longer exists. Do you have a newer link?

@vivekg8667 4 года назад

How to deploy intent classifier model with fast API

@dhyanpatel4680 Год назад

How did you get the model on your google drive and make it downloadable?

@TOpCoder100 4 года назад

Hello, can you make a tutorial on deploying this model on the cloud, plz? Azure | AWS | GCP?

@clivefernandes5435 4 года назад

Hey I was wondering what will be the cost of the of deploying this model ?

@DistortedV12 3 года назад

Does this integrate with kubernetes or docker?

@slimenbouras3184 4 года назад

Great vidéo

@venelin_valkov 4 года назад

The forward method of BertModel can return the hidden states (or just the last hidden state): huggingface.co/transformers/model_doc/bert.html#transformers.BertModel.forward You can apply your pooling strategy on top of that. Here are some you might want to implement: github.com/hanxiao/bert-as-service#q-what-are-the-available-pooling-strategies Best layer? I doubt there is such a thing (would be great if I am wrong, though). I look at this as another hyperparameter - you need to try a lot of values/strategies.