Venkata Hemanth G's repositories
Prompt-Engineering-GPT-Assistants-API-using-RAG
This project showcases the implementation of a prompt engineering using the OpenAI Assistant API, specifically leveraging the Retrieval-Augmented Generation (RAG) system. By integrating cutting-edge language models, the system demonstrates advanced natural language understanding and generation capabilities.
CNN--Image-Classification--Melanoma
Skin Cancer Detection using CNN is a deep learning project that accurately detects melanoma. With a dataset of 2357 skin images, the model alerts dermatologists about melanoma presence, aiding in early detection. It showcases CNN's effectiveness in medical image analysis.
High-Memory-Chat-GPT-3.5-Turbo-ChatBot-Extension.
Developed a cutting-edge browser extension utilizing state-of-the-art language processing technology, including the renowned GPT 3.5 Turbo model. This extension enables users to engage in natural language conversations with an advanced chatbot, which utilizes machine learning algorithms to continuously learn and adapt to user behavior.
Bike_Sharing_Linear_Reg
Predicting the variables that effects the revenue of the bike sharing company after a serious drop-fall during the covid-19 pandemic.
Chest-X-Ray-Effusion-Detection-using-CNN-ResNet
In this X-ray classification assignment, we built a deep learning model to classify chest X-ray images into "nofinding" and "effusion" classes. We tackled challenges like data augmentation, imbalanced classes, and used weighted cross-entropy to improve model performance. The goal was to identify abnormalities with high accuracy.
Image-to-Speech-Generation_Encoder-Attention-Decoder
This project aims to assist visually impaired individuals by providing a solution to convert images into spoken language. Leveraging deep learning and natural language processing, the system processes images, generates descriptive captions, and converts these captions into audio output.
Transformers-based-Text-Summarization
Revolutionize text summarization with this Transformer model, leveraging state-of-the-art techniques. Trained on news articles, it produces concise summaries effortlessly. Explore cutting-edge capabilities for your summarization needs.
CNN-Cats-vs-Dogs-Image-Augmentation-
This project showcases a cats vs dogs image classification model using image augmentation and Keras. It employs deep learning and convolutional neural networks (CNNs) to accurately classify images of cats and dogs.
EDA-Bank-Loan-Default-
To understand the driving factors (or driver variables) behind loan default, i.e. the variables which are strong indicators of loan applicant being defaulter.
Face-Mask-Detection---YOLO
Led development of custom YOLO-based object detector for precise face mask detection in images. Demonstrates expertise in computer vision, deep learning, AI, and image processing. Contributed to pandemic response tech with efficient, accurate model.
Gesture-Control---Conv3D-RNN-LSTM
Transform TV control with Gesture Recognition! Enable intuitive interaction with smart TVs using gestures built using Conv3D, CNN & RNN
ivy
The Unified Machine Learning Framework
Lead-Score-LogReg-ROC-Precision_Recall_Tradeoff
Lead Scoring is such a powerful metric when it comes to quantifying the lead & it is nowadays used by every CRM. In this repository, we are going to take a look at the UpGrad lead scoring case study and see how can we solve this problem through several supervised machine learning models.
Predicting--House-Prices---Linear-Reg--Decision-Trees
Predicting the variables that are highly responsible for house prices in delhi using Linear Regression and decision trees Model.
RSVP_Production_SQL
Giving recommendations to the Top Indian Production team - RSVP ,for their upcoming film about to be released globally.
Sentimental-Analysis.-using-WebScraping-NLP
The objective of this assignment is to extract textual data articles from the given URL using Beautiful Soup and perform text analysis to compute variables that are explained herein.
SpaceShip_Titanic-Prediction
Predicting the transportation of passengers to different planets using systems damaged computer system
Telecom-Churn-Rate
With 226 predictor variables we need to predict whether a particular customer will switch to another telecom provider or not. In telecom terminology, this is referred to as churning and not churning, respectively.
ResNet-CNN---Flower-Image-Classification-
This project uses deep learning to classify flower images as "roses" or "daisies," employing data augmentation, ResNet-18 architecture, and hyperparameter tuning.