Skip to content
View tekboart's full-sized avatar
🎯
Focusing
🎯
Focusing
11 followers · 48 following

Highlights

  • Pro

Block or report tekboart

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tekboart/README.md


               

Hi there, 👋

I'm a 2D/3D Computer Vision (CV) engineer who reseraches on the the applications of CV in Built World. Recently, I have devoloped interest in Robot Learning, epecially mixing it with my CV and Graph ML background, to tackle Robotics-related construction site challenges like SLAM, Localization, 3D Scene Graphs (3DSGs) understanding.

Having worked with various data modalities, such as images, videos, pointclouds, graphs, texts and sensor data, I employ Multimodal AI as the natural way to fuse different data types to tackle Built Environment's complex challenges.

In addition, having been daily driving free software (e.g., Linux, Anki, Drawio, pdftk, etc.), I aspire to learn things to contribute back to the open-source community.

🎯 Research Interests (in order of competency)

  1. 👀 Computer Vision
  2. ❄️ Graph ML
  3. 🤖 Robot Learning
  4. 🥸 Behavioral Cloning & Imitation Learning
  5. 🐘 Distributed Data Processing (Big Data)

🧰 Toolbox

Category Tools
ML & DeepLearning Python PyTorch Tensorflow Keras NumPy Pandas Ray
Computer Vision OpenCV PIL
Agentic AI OpenEnv TorchForge OpenClaw
Graph ML igraph NetworkX PyTorchGeometric TensorFlow GNN DGL
NLP LangChain Ollama
BigData PySpark Hadoop
Database MYSQL Postgresql
Web Development JScript CSS3 HTML5 Django Flask Fast_API
Deployment Docker AWS
Misc Bash Script Vim LaTeX
2D/3D Softwares Blender 3DsMax AutoCad

Pinned Loading

  1. crack-binary-semantic-segmentaion crack-binary-semantic-segmentaion Public

    A Crack Binary Semantic Segmentation Project written purely in PyTorch. Although I have used a crack dataset, one can fine-tune this model with their own binary segmentation data (e.g., medical ima…

    Jupyter Notebook 3

  2. CHB-image_classification_GradCam CHB-image_classification_GradCam Public

    Using four different CNN architectures in an endeavor to detect built heritage in need of preservation and approximately localize the existent damage therein using the GradCam technique.

    Jupyter Notebook 3

  3. SNA-pointcloud SNA-pointcloud Public

    Using Social Network Analysis (SNA) and community detection on point cloud data, in an endeavor to do part segmentation.

    Jupyter Notebook

  4. local-llm local-llm Public

    A secure, local llm powered by Ollama, Langchain, and Streamlit . It supports files attachments including (1) images, (2) texts, (3) spreadsheets, (4) PDFs, and (5) Webpages..

    Python

  5. project-template-ai project-template-ai Public template

    Project Repo Template (With License) for AI research projects. This template uses CI/CD (Github Actions) and supports automatic documentation with Sphinx.

    Makefile