chiragbhuvaneshwara
Computer Science Researcher at DFKI with a solid background in ML-based Computer Vision and interest in Full Stack Development.
Deutsches Forschungszentrum für Küntsliche Intelligenz GmbHSaarbrücken, Germany
Pinned Repositories
AIPCVSeminar
My Presentation Slides and Report from the Advances in Image Processing and Computer Vision Seminar undertaken in WS18/19
cifar10Project
DNN, Simple CNN, Alex Net, VGG Net, GoogLe Net and Resnet trained on CIFAR10 dataset using PyTorch. An associated Web Application developed where an image can be uploaded and classified.
DataNetworks
Assignments completed as part of DataNetworks course at Saarland University in WS18/19
interactive_neural_boxing
Project contains: 1. A trained neural model based on the mixture of experts concept to synthesise fast boxing actions 2. An interactive controller that visualises the results of user controlled motion synthesised with the neural model in Unity.
Learning-to-See-in-the-Dark
Pytorch Implementation of U Net, FPN, GAN using U-Net for correcting images taken in low light.
llmexps
Experiments with OPEN AI API and RAG. Will be updated with PAL, experiments with LLAMA3 etc
MultiTurnNeuralChatbot
In the modern world, a lot of textual data is generated on a daily basis. All of this data can be used to train a deep learning model to respond to queries posed. While many such concepts have already been implemented to respond to the current query, the way the networks are trained is not similar to how humans converse in the real world. In this project, we have developed a new network architecture that will ensure that the network answers the current query not only by considering the current query but also by considering certain important aspects of the previous parts of the conversations.
StatisticalNaturalLanguageProcessing
Assignments and Project completed as part of Statistical Natural Language Processing course at Saarland University in SS18
EASIER-EkmanClassifier
Ekman facial expression classifier trained on affect net and tuned & tested for videos containing Sign Language.
VisualSceneMaker
Visual SceneMaker is an authoring tool for creating interactive presentations aimed to non-programming experts. It supports the modeling of verbal and non-verbal behavior of Virtual Characters and robots. Therefore, it provides users with a graphical interface and a simple scripting language that allows them to create rich and compelling content.
chiragbhuvaneshwara's Repositories
chiragbhuvaneshwara/MultiTurnNeuralChatbot
In the modern world, a lot of textual data is generated on a daily basis. All of this data can be used to train a deep learning model to respond to queries posed. While many such concepts have already been implemented to respond to the current query, the way the networks are trained is not similar to how humans converse in the real world. In this project, we have developed a new network architecture that will ensure that the network answers the current query not only by considering the current query but also by considering certain important aspects of the previous parts of the conversations.
chiragbhuvaneshwara/interactive_neural_boxing
Project contains: 1. A trained neural model based on the mixture of experts concept to synthesise fast boxing actions 2. An interactive controller that visualises the results of user controlled motion synthesised with the neural model in Unity.
chiragbhuvaneshwara/llmexps
Experiments with OPEN AI API and RAG. Will be updated with PAL, experiments with LLAMA3 etc
chiragbhuvaneshwara/cifar10Project
DNN, Simple CNN, Alex Net, VGG Net, GoogLe Net and Resnet trained on CIFAR10 dataset using PyTorch. An associated Web Application developed where an image can be uploaded and classified.
chiragbhuvaneshwara/StatisticalNaturalLanguageProcessing
Assignments and Project completed as part of Statistical Natural Language Processing course at Saarland University in SS18
chiragbhuvaneshwara/AIPCVSeminar
My Presentation Slides and Report from the Advances in Image Processing and Computer Vision Seminar undertaken in WS18/19
chiragbhuvaneshwara/DataNetworks
Assignments completed as part of DataNetworks course at Saarland University in WS18/19
chiragbhuvaneshwara/DSP
Assignments and Projects completed as part of the Digital Signal Processing course at Saarland University in SS19
chiragbhuvaneshwara/HLCV
Projects completed as part of the High Level Computer Vision course at Saarland University in SS19
chiragbhuvaneshwara/Learning-to-See-in-the-Dark
Pytorch Implementation of U Net, FPN, GAN using U-Net for correcting images taken in low light.
chiragbhuvaneshwara/EmotionDashboard
chiragbhuvaneshwara/IntroToDataScience
Assignments, Projects and additional stuff from EdX course Introduction to Computational Thinking and Data Science
chiragbhuvaneshwara/MLCySec
Projects completed while partaking Machine Learning in Cybersecurity course at Saarland University in WS18/19
chiragbhuvaneshwara/MoMA-Project
Image Compression using PCA implemented as a required project for Methods of Mathematical Analysis(MoMA) at Saarland University in WS17/18
chiragbhuvaneshwara/NeuralNetworks
Assignments and projects associated with Neural Networks Implementation & Application Course in WS17/18 at Saarland University
chiragbhuvaneshwara/Python
Assignments, projects and additional stuff from the EdX course Intro to Computer Science using Python
chiragbhuvaneshwara/resume
chiragbhuvaneshwara/StatsWithR
Assignments completed as part of the Statistics with R course at Saarland University in WS18/19