99sbr / Sentiment-Analysis-Web-App

Sentiment Analysis Flask-Restplus based Web app. The backed model is BERT powering the classification Engine.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Sentiment-Analysis-Web-App 🤖 : Built Using Flask-Restplus

  • The Flask API structured as follow: Image

  • manage.py is the main file to run the application.

  • gunicorn --bind 0.0.0.0:5000 manage:application command to run the application

  • The app is designed for BERT model trained on sentiment analysis data. The is only inference API.

  • PRE_TRAINED_MODEL_NAME = 'bert-base-cased'

  • Deployed on ec2 instance : Deep Learning AMI (Ubuntu 18.04) Version 35.0

About

Sentiment Analysis Flask-Restplus based Web app. The backed model is BERT powering the classification Engine.


Languages

Language:Jupyter Notebook 97.1%Language:Python 2.9%Language:Dockerfile 0.1%