Training Sentiment Model Using BERT and Serving it with Flask API
In this video, I will show you how you can train your own #sentiment model using #BERT as base model and then serve the model using #flask rest api.
The video focuses on creation of data loaders, creating a bert model using transformers python library, training the model and then doing inference using flask.
The model described here can achieve an accuracy of 93% on IMDB 50K Movie Reviews data set.
The training dataset can be found here: https://www.kaggle.com/lakshmi25npath...
Bert base uncased files used in this video can be downloaded from here: https://www.kaggle.com/abhishek/bert-...
Github repo with all the code will be shared after the premier.!
Like, Subscribe & Share ;)
#Sentiment #BERT #DeepLearning
Follow me on:
Twitter: / abhi1thakur
LinkedIn: / abhi1thakur
Kaggle: https://kaggle.com/abhishek