Skip to content

harshidkoladara/AutoGML

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AutoGML

AutoGML is a Graphical User Interface based Automated Machine Learning System which provides a Machine Learning model without writing a single line of code. AutoGML makes the power of ML available to everyone even if they have limited or no knowledge of ML. AutoGML reduces developer efforts to build machine learning system from days to hours. AutoGML have features like AutoGML Tables, Image Classification, Object Detection, Face Detection and API. AutoGML Tables enables you to automatically build and deploy state-of-the-art machine learning models on structured data at massively increased speed and scale by importing datasets and a few clicks and then deploy it to in your system. AutoGML Image Classification, Object Detection and Face Detection enables enables you to train machine learning models to classify your images according to your own defined labels.

Currunt Problem

Today, Machine Learning and Artificial Intelligence is a big hype in the IT industry. Their goal is to improve user experience, But the Machine Learning is a most complex to implement and developers can not work with ML Algorithms. So, they need to hire ML Engineers and Data Scientists to embed ML into their system which is too costly and also time consuming. For the experienced Data Scientists and ML Engineers it's too much hard and time consuming to make models with acceptable accuracy because it includes many steps on data preprocessing and Hyperparameter tuning.

Limitation of existing system

Mostly ML and AI systems is developed by ML engineer and Data Scientists which is very much costly and time consuming.

To develop ML and AI system, it requires high-end systems and too much computation power, which is not afforded by everyone.

Tech giants like Google is provided a AutoML to users but it is very costly for average developer to use and charge per single train and usage, also it provides only in-system use and API. System developed by this must be connected to internet all the time.

Proposed System

AutoGML - Automated Graphical based Machine Learning is a Graphical User Interface based Automated Machine Learning System which provides a Machine Learning model without writing a single line of code.

AutoGML makes the power of machine learning available to everyone even if they have limited or no knowledge of machine learning.

AutoGML reduces developers efforts to build machine learning system from days to hours. By using AutoGML, We can build machine learning capabilities to create our own custom machine learning models that are tailored to our business needs, and then we can integrate those models into our applications and websites.

AutoGML provides a trained models for later use and developers can include them into their system with small line of code which is also provided by our system and user can use power of machine without internet connection.

Developer can use ML by any way in-system and can later use with just download without any additional cost.

Tools and Technology

Machine Learning Deep Learning Neural Networks Python HTML5 / CSS3 / BootStrap4 AJAX

#Frameworks Django TensorFlow Keras Scikit-Learn Numpy Pandas Matplotlib

Future Scope

Our future goal is to develop efficient and fully optimized system that can fulfil any condition and develop accurate Machine Learning model for it.

After completed whole project, lunch it on global platform and make available for whole developers community in couple of years.

Integrate API service with system, So user can use their custom developed model with any service and embed them into their project.

Provide Pre-build APIs to user, So user can use these APIs of custom ML models and use them without any training efforts.

Make in-app purchase system available, so it can generate revenue for our team.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors