Harbhajan Singh's Projects
A curated list of references for MLOps
Links to awesome OCR projects
One of the challenge for all Pharmaceutical companies is to understand the persistency of drug as per the physician prescription. With an objective to gather insights on the factors that are impacting the persistency, build a classification for the given dataset.
A Comparative Study of Dimensionality Reduction Methods and Clustering Models for Single-Cell RNA Seq Data
Final project of COMP8347-Internet Application & Distributed System course
Assignment works of course "COMP8610 - Neural Networks and Deep Learning"
In this projects, we will compare the accuracy and other metrics of different classification model on different datasets.
In this repository, I will compare the different clustering techniques on different datasets and calculate values of K using two different methods.
Finding the coordinates points for wrist watch for human. It can be used for Augmented Reality to try the watch in real time by realtime try-on.
Covid19 Patients Records App Using Streamlit and Heroku
Nowadays, industries adopt data science to better understand their customer’s activity and differentiate their offerings from their competitor. For deploying customer segmentation in e-commerce, data mining approaches like clustering and subgroup discovery will be used. Combining new marketing strategies with word-of-mouth recommendations is become very important for making any successful business model. Due to a large diversity of products, their features, and sales makes it difficult to find the patterns of customer’s preferences. For achieving optimum segmentation, we used the clustering techniques to classify the customers based on their online purchasing based on different categories. The goal of this paper how the customer makes purchasing patterns and divides them into segments on which we can enable practitioners for term profitability by retaining and gaining the customers. It may also help e-commerce companies in their business model to retain and gain customers.
This repository will extract the data of Top 50 stocks of Canadian Stock market since 2010.
Cheat Sheets
Data Science Assignment
In this Facebook live code along session with Hugo Bowne-Anderson, you're going to check out Google trends data of keywords 'diet', 'gym' and 'finance' to see how they vary over time.
The Data Scientist's ToolBox
The Leek group guide to data sharing
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
A Comprehensive Study of Different Deep Neural Network Architectures for Traffic Sign Classification
Digit Recognization
Discussed the results achieved by dimensionality reduction and clustering using Principal Component Analysis and Kernel Principal Component Analysis.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
The Drowsiness Detection Python project is a real-time system designed to detect drowsiness in a person based on certain physiological and behavioral patterns. It uses computer vision techniques and machine learning algorithms to monitor the person’s eyes, specifically the aspect ratio of the eye’s width to its height
Personalizing LLM Responses
Face Mask Detection using NVIDIA Transfer Learning Toolkit (TLT) and DeepStream for COVID-19
It is a meal delivery company which operates in multiple cities. They have various fulfillment centers in these cities for dispatching meal orders to their customers. The client wants you to help these centers with demand forecasting for upcoming weeks so that these centers will plan the stock of raw materials accordingly.
Generated two types of datasets: 3D S-shape and Swiss Roll. Plot the 3D visualization of both datasets then apply manifold learning methods like Isomap, Laplacian Eigenmaps and Locally Linear Embedding(LLE) to obtain new “unrolled” data on the 2D space.
Sample code and notebooks for Generative AI on Google Cloud
Hackerrank Python Certification Solution