Use deep learning model to produce a pixel-by-pixel classification of images and identify road for autonomous driving vehicles

Train a Seq2Seq Model with Attention to Translate from One Language to Another

A SegNet model trained for segmentation of Lanes suitable for driving for automobiles.

This project is about training a deep neural network to identify and track a target in simulation using Udacity's RoboND drone simulator. 🛸 Applications like this are key to many fields of robotics and the techniques applied can be extended to scenarios like advanced cruise control in autonomous vehicles or human-robot collaboration. 👨‍🏫

A systematic way to convert verbatim medical terms with the proposed encoder/decoder+attention block solution. (python, TensorFlow)

Generate Images from text prompt using Stable Diffusion Model

A deep learning model that achieves video super-resolution tasks with temporal and spatial attention in cascade

This GitHub repository houses an innovative implementation of Neural Machine Translation (NMT) using state-of-the-art sequence-to-sequence networks. The primary focus is on enhancing translation quality through progressively advanced architectural improvements.

Image Colorization Models for Urban Landscapes Using Pytorch

A seq2seq model using LSTM-based encoder-decoder architecture for metadata generation from code snippets, optimizing software maintenance process

I implement encoder-decoder based seq2seq models with attention using Keras. The encoder can be a Bidirectional LSTM, a simple LSTM, or a GRU, and the decoder can be an LSTM or a GRU. I evaluate the models on an English-French dataset.

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.

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

My implementation of autoencoders

Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

Chatbot using Transformer Model and DialoGPT