Name: SUMAN PAUL CHOUDHURY
Type: User
Company: Sahaj Softwares , Bangalore
Bio: A machine learning and deep learning enthusiast , Data Science consultant - Sahaj Softwares , Bangalore
Currently focusing on Big Data and Analytics
Location: Bengaluru
SUMAN PAUL CHOUDHURY's Projects
This project is an attempt to develop a solution where the damage assessment could be done automatically through images for passenger vehicles
The dataset contains 3 folders containing images which describes the intensity of damages as minor , moderate and severe accordingly. The task was to analyse and explore the different feature extraction techniques along with classifiers to check upon the performance of the system. Hereby I worked with 3 different types of approaches to tackle the task
this contains all the data required for project in this github
contains small datasets for experimentation purposes
This is a end to end project implementation using mlops
:camera: :computer: OpenCV 3.1.0 + Python mini-projects using Ubuntu 14.04 LTS and Odroid-XU4
This repository contains all the codes related to langchain , llamaindex and openai. I will keep on updating as in when I keep on reading more documents
This project focusses on automatic car recognition which was build using pretrained models
Hand Signs corresponding to digits 0 to 5 are detected using CNN . The programs are being written in Tensorflow
This project explores the power of a predictive model that has been trained and tested over the boston housing data set
This project takes a low resolution images and tries to generate a high resolution images which looks as realistic as possible. This is achieved by using GANs.
The objective of the project is that given a query image, it will find 3 most similar image from the given image directory
This repo contains all the material required to understand how to track your experiments using MLflow
This project is an end to end implementation of a deep learning project using MLOPS
Open Source Computer Vision Library
In this project we will try to predict the stock price of Google using LSTM. Though the future stock price does not depend on the past, but we can observe some trend. We will try to predict the upward and downward trend that exist in Google stocks and this would be done using LSTM (a special case of RNN's). We are going to implement a robust LSTM with stacked layers. We are also going to add drop outs and regularizers to avoid overfitting.