Порождение подписей к изображениям. Классификация изображений. Прогнозирование временных рядов

Blip 2 Captioning, Mass Captioning, Question Answering, and other tools.

Image Captioner Model

Generates textual description of any given image. Use both Natural Language Processing (NLP) and Computer Vision to generate captions. The idea implemented is to replace the encoder (RNN layer) in an encoder-decoder architecture with a deep Convolutional Neural Network (CNN) trained to classify objects in images.

Deep Learning Photo Caption Generator Tensorflow 2.0

This repository trains image captioning model using CNN and Transformers.

A model inspired from the famous Show and Tell Model is implemented for automatic image captioning.

Click below to checkout the website

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.

BLIP-ImageCaption

Image Captioning is the task of describing the content of an image in words. This task lies at the intersection of computer vision and natural language processing.

Personalized Image Captioning with Transformer Models

Giving short discription of Image using AI

image caption generator, dog breed classifier, stock forecasting 🤖🖼️ Порождение подписей на русском языке к изображениям (Python, Keras). Собрал нейросеть из двух частей – свёрточная и рекуррентная части. Получил датасет путём перевода на русский датасета Flickr 8k с помощью Yandex Translate API. Получил метрику BLEU равной 0.51.

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

This project Implements a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to generate descriptive captions for input images.

Streamline the creation of supervised datasets to facilitate data augmentation for deep learning architectures focused on image captioning. The core framework leverages MiniGPT-4, complemented by the pre-trained Vicuna model, which boasts 13 billion parameters.

Successfully developed an image caption generation model which can precisely generate the text caption of any particular image based on a certain vocabulary of distinct words.