Pratheesh's repositories
CricketShotClassification
Collaborative project by Ritik Bompilwar and Pratheesh. This repository focuses on classifying cricket shots using advanced machine learning techniques. Equal contributions were made in developing and optimizing the model to enhance accuracy and performance.
SketchGAN
Sketch-to-Image Criminal Identification System using a pix2pix GAN trained on the CUHK dataset to generate realistic images from sketches. A classifier is then trained on mugshot data to identify individuals based on generated images, enhancing forensic sketch recognition with deep learning for accurate identification.
CLIP-MemeSense
MemeSense leverages CLIP for multimodal meme analysis, integrating vision and language features through cosine similarity to classify humor, hate speech,stance.
Neural-machine-translation
neural machine translation using attention mechanism which translates eng sentences into its corresponding hindi translations
SegwayVision
The project utilizes convolutional-based network architectures for semantic image segmentation. This project utilizes the Indian Driving Dataset (IDD) Lite to classify various elements in Indian road scenes into 8 predefined categories. This implementation utilizes FCN - VGG backbone, U-Net, LINKNet, and DEEPLABV3+.
StockManagement
Developed a robust stock management application integrating design patterns such as Facade, Builder, MVC, SOLID principles, and Command patterns, focusing on abstraction and code reusability to ensure scalability and extensibility.
-Emojifier
Thisproject aims at developing a model which inputs a sentence and finds the most appropriate emoji to be used with this sentence to make the text messages more expressive.It uses the LSTM layers to learn the long range dependencies in the text.
BERT-Sentiment-FlightReview
Fine-tuning a BERT-based model for sentiment analysis of airline tweets. This project classifies textual feedback into positive, negative, or neutral categories, demonstrating the effective application of transformer models to analyze and gain insights from real-world airline service feedback.
Document-based-Question-Answering-System
This project demonstrates a Retrieval-Augmented Generation (RAG) system for question answering. It integrates OpenAI’s GPT-4 model with FAISS for vector similarity search, enabling the system to provide accurate and contextually relevant answers based on a given document or dataset.
getdns
A modern asynchronous DNS API https://getdnsapi.net/
PcapPlusPlus
PcapPlusPlus is a multiplatform C++ library for capturing, parsing and crafting of network packets. It is designed to be efficient, powerful and easy to use. It provides C++ wrappers for the most popular packet processing engines such as libpcap, WinPcap, DPDK and PF_RING.
Plant-pathology
This repository develops deep learning solutions for classifying plant diseases, using models like DenseNet121, EfficientNetB1, and EfficientNetB2, enhanced with ensemble techniques such as average ensemble and soft voting. Aimed at automating plant disease detection to improve agricultural productivity.
Real-Time-Vehicle-Detection-and-Traffic-Flow-Classification-System-
This project uses YOLOv8 for real-time vehicle detection, classifying traffic on custom datasets. It processes image and video inputs, providing metrics like vehicle counts and traffic density. The model, exportable in PyTorch and ONNX formats, supports deployment across various platforms for traffic management and smart city applications.
ShakespeareGen
Explore AI-powered text generation with a character-level transformer model that mimics Shakespeare’s style.
Transformer
Transformer-based Neural Machine Translation model for English to Italian, built with PyTorch and Hugging Face’s transformers. This project includes full training and inference capabilities, and is designed to demonstrate the implementation of the architecture as described in the ‘Attention is All You Need’ paper.
gt-nlp-class
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
openai-cookbook
Examples and guides for using the OpenAI API
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.