we generate captions to the images which are given by user(user input) using prompt engineering and Generative AI

This Project is based on multilingual Translation by using the Transformer with an encoder-decoder architecture along with the multi-head self-attention layers with the positional encoding and embedding for better result and accuracy. Overall, this model converts the English to French language using various Techniques of NLP and DL.

TransRUPNet for Improved Out-of-Distribution Generalization in Polyp Segmentation (IEEE EMBC)

My implementation of autoencoders

Using to predict the highway traffic speed

Sequence-to-Sequence Generative Model for Sequential Recommender System

the repository describes an attempt to make an image dehazer using autoencoders

This repository consist of projects related to Natural Language Processing using machine learning and deep learning concepts

This GitHub repository contains the implementation of a deep learning model capable of generating captions for images in the form of speech.

Annotated vanilla implementation in PyTorch of the Transformer model introduced in 'Attention Is All You Need'

Deep learning model to predict the normal flow between two consecutive frames, being the normal flow the projection of the optical flow on the gradient directions.

A solution to American Sign Language Detection using Deep Learning

An LLM based tool for generation of cheese advirtisements

An Online URL Encode Decode Tool to convert content into ASCII character-set. Our tool uses in-built JavaScript function for encoding.

Official implementation of the ICASSP-2022 paper "Text2Poster: Laying Out Stylized Texts on Retrieved Images"

This Repository Contains the code implementation for neural machine translation between Tanglish and English

Repository containing the codes used for the development of a heart sound prediction system using convolutional neural networks (CNN) for semantic segmentation.

Image captioning with a benchmark of CNN-based encoder and GRU-based inject-type (init-inject, pre-inject, par-inject) and merge decoder architectures

The Positional Encoder Decoder is a Visual Basic .NET class that provides functionality for encoding and decoding tokens and sentences using positional embeddings. It allows you to convert between string tokens and their corresponding embeddings, and vice versa.