OMKAR GURAV's repositories
Soil-Type-Classification
https://soilnet.herokuapp.com/ Created a Soil Classification model using Deep Learning which also suggests Crops in 6 different languages and deployed on Heroku. Soil Classification is one of the most important topics, for Farmers and Agriculture Researchers.
Telegram-Bot-for-Model-Training-Updates
Created a Telegram Bot that will send message after every Epoch regarding Training & Validation Accuracy, Loss and Graph too.
Loan-Approval-Prediction
Loan Approval Prediction Problem Type Binary Classification Training Accuracy 84% Loan approval prediction is classic problem to learn and apply lots of data analysis techniques to create best classification model. Given with the data set consisting of details of applicants loan and status whether the loan application is approved or not. Basis on this a binary classification model is to create with maximum accuracy.
Agri-Intelligence
An Agri Culture project with 3 modules, 1.Soil Type Classification and Crop Suggestion, 2. Crop Disease Detection, 3.Agriculture Chat Bot in 6 Languages deployed on cloud and can be accessed at below link...
Computer-Vision---Object-Detection-in-Python
Object detection (faces, humans, cars) using OpenCV in Python
device_me
Get user device information.
Diabetes--EDA-Acc_89-F1-Score_89-Precision_89.5-
Results=Top Acc=89,Benchmark : 75.97=Without any processing, XGBoost : 87.50=After Distribution Normalization + Up-Sampling + Feature Selection,XGBoost & Random Forest : 89.00=After Distribution Normalization + Up-Sampling + Feature Selection + Fine Tuning + Random State in Data Spliting,Gradient Boosting Classifier : 92.20=After removing outliers
Face-Mask-Detection
Created a model that detects face mask trained on 7553 images with 3 color channels (RGB). On Custom CNN architecture Model training accuracy reached 94% and Validation accuracy 96%.
Flag-On-Face-OpenCV
Adding Indian Flag Badge on face as sticker on both cheeks without using "dlib" or any Facial Key Points Extraction.