The objective is to process by generating textual description from an image – based on the objects and actions in the image. Using generative models so that it creates novel sentences. Pipeline type models uses two separate learning process, one for language modelling and other for image recognition. It first identifies objects in image and prov…

Download flickr8k, flickr30k image caption datasets

PyTorch implementation of 'CLIP' (Radford et al., 2021) from scratch and training it on Flickr8k + Flickr30k

An attention based sequential deep learning model implemented in pytorch to generate single line caption given an input image

Deep Learning Final project 2022

Library for training visually-grounded models of spoken language understanding.

Image Captioning is a task where each image must be understood properly and are able generate suitable caption with proper grammatical structure. Here it is a hybrid system which uses multilayer CNN (Convolutional Neural Network) for generating keywords.

A Deep-Learning based web app that generates image captions using a pre-trained CNN-LSTM model. Upload your own image or use sample ones to see AI describe them in natural language. Built with TensorFlow, trained on Flickr8k, and combines computer vision with NLP.

Implemented the Variational AutoEnoder and Decoder

Exercise on captioning images in the Neural Networks for Computer Vision course. Using the Flickr8K dataset, and simple encoder-decoder architecture. Evaluation based on Cross-Entropy loss and 4-gram Bleu score.

Generate natural language captions for images using the BLIP vision-language model by Salesforce. Easily run it in Google Colab with GPU support, using the Flickr8k-2k image dataset from Kaggle.

A repository hosting the complete Flickr8k dataset, prepared and ready for image captioning research.

Image Captioning using Encoder Decoder network , Pretrained models given