8000 Shubham-Sahoo (Shubham Sahoo) Β· GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View Shubham-Sahoo's full-sized avatar
:octocat:
:octocat:
  • NeuroPixel.AI
  • Bengaluru, India

Highlights

  • Pro

Block or report Shubham-Sahoo

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
shubham-sahoo/README.md

Hi there πŸ‘‹, I'm Shubham Sahoo!

Welcome to my GitHub profile! I'm a passionate Software Engineer, problem solver, and AI enthusiast who thrives on building impactful projects and exploring cutting-edge technologies.


πŸš€ About Me

  • 🌱 I’m currently learning Multimodal systems training and Virtual Try-On (VTON) systems
  • πŸ’» I’m working on Finetuning Diffusion models, Model optimization using TensorRT, and Scalable AI deployment pipelines.
  • 🎯 Goals for 2025: Contribute to foundational AI research, optimize real-world AI applications, and mentor aspiring engineers.
  • ❀️ I’m passionate about Deep Learning, Computer Vision, and Generative AI.
  • πŸ“« How to reach me: shubhamsomnath@gmail.com.

πŸ”§ Technologies & Tools

  • Programming Languages: Python, C++, CUDA
  • Frameworks: PyTorch, OpenCV, FastAPI
  • Tools & Technologies: TensorRT, Git, Docker, Kubernetes, Kafka

πŸ“ˆ GitHub Stats

Shubham-Sahoo's GitHub stats


🌟 Featured Projects

  • Built Eklavya 7.0, a self-driving robot capable of autonomous navigation and obstacle avoidance.
  • Developed motion control, tuned EKF-based localization, and designed the robot's electronic architecture.
  • Designed Multilevel Feedback Queue Scheduling in PintOS to enhance performance fairness.
  • Developed a multiple producer-consumer system using shared memory to avoid deadlocks.
  • Implemented reinforcement learning algorithms for robotic arm control and precision tasks.
  • Achieved 10% increase in task efficiency using DDPG and SAC algorithms.

🌐 Let's Connect!


Thanks for visiting my profile! 😊

Pinned Loading

  1. CUDA-Optimized-Centrality-Measure CUDA-Optimized-Centrality-Measure Public

    Forked from JaydeepGodbole/centrality_measures_gpu

    CUDA optimized version of Page Rank and Betweenness Centrality Algorithms, tested on large graphs (Facebook, etc.)

    Jupyter Notebook 1

  2. Obstacle-Avoidance-on-UAV Obstacle-Avoidance-on-UAV Public

    Obstacle Avoidance Package that can be directly used on PX4 flight controller and also in simulation environment GAZEBO

    5 1

  3. Safety-Driving-Assist Safety-Driving-Assist Public

    Forked from reyanshsolis/safety_driving_assist

    Driver assist system to warn/stop the vehicle based on alertness score, calculated based on facial expressions.

    Jupyter Notebook 1

  4. Image_inpainting Image_inpainting Public

    "Region Filling and Object Removal by Exemplar-Based Image Inpainting" by Criminisi et al

    MATLAB 2

  5. kornia kornia Public

    Forked from kornia/kornia

    🐍 Geometric Computer Vision Library for Spatial AI

    Python

  6. pytorch pytorch Public

    Forked from pytorch/pytorch

    Tensors and Dynamic neural networks in Python with strong GPU acceleration

    Python

0