Multi-Modal learning toolkit based on PaddlePaddle and PyTorch, supporting multiple applications such as multi-modal classification, cross-modal retrieval and image caption.

Image to LaTeX (Seq2seq + Attention with Beam Search) - Tensorflow

Pytorch implemention of Deep CNN Encoder + LSTM Decoder with Attention for Image to Latex

Image captioning ready-to-go inference: show and tell model compatible with Tensorflow r1.9

Code of Dense Relational Captioning

Code for GHA (ACCV2018)

Repo for Implementing Research Papers & Projects related to Machine Learning

ImageCaptioning improved with an attention mechanism. Also a PyQt5 application

Generating Captions for images using CNN & LSTM on Flickr8K dataset.The generation of captions from images has various practical benefits, ranging from aiding the visually impaired.

Some interesting applications of RNN, e.g. char rnn (pomes generation), seq2seq (machine translation), image captioning (NIC)

An implementation of the paper "Context-aware Captions from Context-agnostic Supervision"

A dockerised web-app to generate captions for uploaded images.

TensorFlow-2 implementation of Im2Latex deep learning model described in HarvardNLP paper "What You Get Is What You See: A Visual Markup Decompiler"

An App with Voice Assisted Image Captioning and VQA For Visually Challenged Individuals

Implementation of various basic layers forward and back propagation. CS 231n Stanford Spring 2018: Convolutional Neural Networks for Visual Recognition. Solutions to Assignments

AI Poet who looks at the images and writes poems Web service.

A CNN model to predict the scene or location from any given image

ImgCap is an image captioning model designed to automatically generate descriptive captions for images. It has two versions CNN + LSTM model and CNN + LSTM + Attention mechanism model.

Generative AI Models is a comprehensive repository dedicated to the implementation of cutting-edge generative AI models using Python. It features various models, including those for image captioning and text-to-image generation, leveraging advanced architectures like Vision Transformers (ViT), GPT-2, and Stable Diffusion.

cs231n assignments.