Computer Science and Programming
15.2K subscribers
102 photos
15 videos
24 files
219 links
Channel for who have a passion for -
* Artificial Intelligence
* Machine Learning
* Deep Learning
* Data Science
* Computer vision
* Image Processing
* Research Papers
* Related Courses and Ebooks

With advertising offers contact: @ai_adminn
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
AiOS: The Future of Human Shape & Pose Recovery

Discover AiOS, the cutting-edge, unified framework by SenseTime, HKU, IDEA, S-Lab, and Shanghai AI Lab. AiOS redefines state-of-the-art expressive pose and shape recovery, seamlessly integrating advanced features without the need for separate human detection steps.

Highlights:

First-of-its-Kind: Single-stage EHPS with zero extra detection networks.
Innovative Design: Unique "Human-as-Tokens" concept for deeper insights.
Enhanced Dynamics: Sophisticated attention to human relationships.
Comprehensive Analysis: Unified feature system for unparalleled whole-body understanding.
Unmatched Performance: Top-tier results sans ground truth bounding boxes.

Explore More:
Project Page
Read the Paper

@MachineLearning_Programming
LeGrad: Layerwise Explainability GRADient method for large ViT transformer architectures

Explore More:
💻DEMO:
you may use demo
📖Read the Paper:
Access Here
💻Source Code: Explore on GitHub

Relevance:
#AI #machinelearning #deeplearning #computervision

join our community:
👉
@MachineLearning_Programming
msg609873512-965877.jpg
120 KB
🚀 Explore AI News with Us! 🤖

Looking for top-notch AI updates?
Don't miss out on our Telegram channel!
We offer daily insights into the latest advancements, research papers, and industry news.

🔗 Join now: https://t.me/Artificial_Intelligence_Updates

Join our community of AI enthusiasts and stay ahead of the curve! 🌐
India's Largest Free Webinar on LLMs especially focused on the recently released LLAMA-3 by Meta.

How do you use these models?
How can you create apps with them?

Join our free workshop on to learn how to use Llama 3 and create apps with it.

Register here: https://www.buildfastwithai.com/events/llama-3-deep-dive

You can connect with Founder;
https://www.linkedin.com/in/satvik-paramkusham/

This Event is especially designed for people interested in the field of AI, ML, GenAI & LLMs.
Learn to deploy Gen Ai Models to production 👇

MLOps Masterclass

Productionizing Generative AI models, Navigating the Landscape of MLOps & LLMOps - Understanding the Synergy


Schedule:
May 25th (Sat) & 26th (Sun), 10AM to 3:30 PM


Register Now👇
https://bit.ly/mlops-masterclass

🔥 Limited Seats Available!

☎️ Contact:
Sarath Kumar
+918940876397 / +918778033930
Result.gif
23.1 MB
🚀 Discover LiteHPE: Advanced Head Pose Estimation 🚀

Features:
🛠️ Setup in Minutes:
📈 Top-Tier Performance:
Achieve low Mean Absolute Error rates
Models range from MobileOne_s0 to s4
Pretrained models ready for download

🌟 🌟 Star us on GitHub for the latest updates: LiteHPE on GitHub.

Boost your project's capabilities with LiteHPE – the forefront of head pose estimation technology!

#AI #MachineLearning #HeadPoseEstimation #Technology #DeepLearning

🔗 Join now:
@MachineLearning_Programming
🌟 Join Our Team as a Senior Data Researcher at Wunder Fund! 🌟

🚀 Location: Remote/Relocation to various countries
💸 Salary: $5k-$7k+ per month (USD or Crypto)


At wunderfund.io we've been in the HFT trading game since 2014 and our daily trading volume is around $8B. We're looking for a Senior Data Researcher to lead our neural networks direction.

👾What You’ll Do:

- Train models, test hypotheses, and achieve maximum model accuracy
- Work with top-tier programmers, mathematicians, and physicists

🤓What You Will Need:

- Proficiency in Python and Mathematics
- Experience with Kaggle (Master/Grandmaster)
- Success in training transformers and LSTM

🌐 Learn More & Apply
00001.gif
5.8 MB
3D Shot Posture Dataset

This dataset consists of the 3d and 2d postures of professional football players under shot situations.

Content of the dataset:
In 3dsp/train
20 cropped image x 200 shot
Tracklet, 2d and 3d keypoints
In 3dsp/test
20 cropped image x 10 shots
Tracklet

https://github.com/calvinyeungck/3D-Shot-Posture-Dataset

join our community:
👉
@MachineLearning_Programming
Are you struggling with invoking functions, passing arguments, or handling return values in Large Language Models (LLMs)?

Whether you’re a seasoned developer or just starting your journey in Gen AI.

In this session, we’ll explore the fascinating world of invoking functions using LLMs.

1. Introduction to LLMs.
2. Function Calls: Basics and Syntax.
3. Live Coding Examples.
4. Q&A Session.

Register For Free:
🗓 Date: 14th June, Friday
Time: 9 PM, IST
🔗 Link : https://www.buildfastwithai.com/events/function-calling-with-llms
This media is not supported in your browser
VIEW IN TELEGRAM
Ultralytics YOLOv8 for Smarter Parking Management Systems


💻Project Details:
Discover More


🔗 Join now: @MachineLearning_Programming
Please open Telegram to view this post
VIEW IN TELEGRAM
🚀 MLOps Market to reach US$4 Billion in 2025

Unleash MLOps Mastery - FREE Training on AWS, Azure, GCP & Open-source!

Navigating the Landscape of MLOps & LLMOps

🌟 Unlock ML deployment secrets on top clouds & open source.
💡 Dive into data management insights.
🛠️ Harness the latest MLOps tools.
👥 Real-time expert interaction.

🔥 Limited spots! Enroll now:
https://bit.ly/mlops-free-class

🚀 Share with ML enthusiasts! #MLOps #AI #TechTraining
This media is not supported in your browser
VIEW IN TELEGRAM
🔗 GitHub_Link

❇️ MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

#Mesh

Join my channel: @MachineLearning_Programming
This media is not supported in your browser
VIEW IN TELEGRAM
🕹 VideoLLaMA 2: Open-Source Video-LLMs for Video Generation

VideoLLaMA 2 is a cutting-edge set of open-source Video-LLMs designed for advanced video generation. Building on the successes of previous models, VideoLLaMA 2 introduces a specialized space-time convolution (STC) component, enabling it to effectively capture complex dynamics in video.


🔗 Resources:
🖥 GitHub
🤗 Demo
VideoLLaMA 2 Model

Explore the capabilities of VideoLLaMA 2 and revolutionize your video generation projects!
output_demo.gif
21.2 MB
🌟FACE ID: Face Identification 🌟


Hello tech enthusiasts! 🚀

Our project leverages the power of ONNX Runtime to deliver high-accuracy face identification.

🎉 Check out our project and see it in action!

🔗 Visit our GitHub Repository: FACE ID

We need your support to make this project even better! Here’s how you can help:

⭐️ Star our repository to show your appreciation and help us gain more visibility.
🔄 Share with your network to spread the word about Face ID.
📝 Give us feedback by reviewing the code and suggesting improvements.


Thank you for being part of our journey. Let's create something amazing! 🌟

#FaceRecognition #ONNX #AdaFace #GitHub #OpenSource #TechInnovation

Happy Learning! 🌟
80+ Python Coding Challenges for Beginners.pdf
525 KB
📚 Title: 80+ Python Coding Challenges for Beginners (2024)

Why Python? Why This Book?
* Progressive Learning.
* Challenge Variety
* Interactive and Engaging
* Real-World Applications
* Beyond the Basics


Happy Learning! 🌟
@MachineLearning_Programming
demo.gif
6.5 MB
🚀 3DGazeNet: Revolutionizing Gaze Estimation with Weak-Supervision! 🌟

Key Features:
🔹 Advanced Neural Network:
Built on the robust U2-Net architecture.
🔹 Comprehensive Utilities:
Easy data loading, preprocessing, and augmentation.
🔹 Seamless Integration:
Train, test, and visualize with simple commands.

Demo Visualization:Visualize the demo by configuring your video path in main.py and showcasing the power of 3DGazeNet.

Pretrained Weights:Quick start with our pretrained weights stored in the weights folder.

💻Source Code: https://github.com/Shohruh72/3DGazeNet
📖Read the Paper: Access Here


#3DGazeNet #GazeEstimation #AI #DeepLearning #TechInnovation

Join us in pushing the boundaries of gaze estimation technology with 3DGazeNet!
demo2.gif
14.3 MB
🚀 Bring Your Portraits to Life with LivePortrait AI! 🚀

🎨 Introducing LivePortrait: The Ultimate Tool for Animated Portraits 🎨

🔍 Features:

One-Click Animation: Generate animated portraits effortlessly.
🔍 Keypoint Detection: Precise facial keypoint transformation.
🎥 Video Processing: Drive animations with video inputs.
🔧 Model Integration: Seamlessly combines various advanced models.
📄 Template Creation: Create consistent and repeatable motion templates.

Why LivePortrait?

User-Friendly:
Intuitive design for easy use.
High-Quality Animations: Realistic and captivating results.

🔗 Check it out on GitHub:
LivePortrait AI GitHub Repository

#Watch_the_magic_with_one_click

⭐️ Give us a star and join the revolution in portrait animation! ⭐️

@MachineLearning_Programming
result.gif
17.7 MB
🚀 Aruco Pose Estimator: Elevate Your Vision Projects!
🎯 Why Aruco Pose Estimator?

Real-Time Detection:
Seamlessly detect ArUco markers in live video feeds.
3D Pose Estimation:
Accurately estimate the orientation and position of markers.
Comprehensive Metrics:
Get real-time pitch, yaw, roll, and distance estimations.

Key Features:

Real-Time Detection:
Detects ArUco markers instantly.
3D Pose Estimation:
Provides precise orientation and position.
Orientation Metrics:
Calculates and displays pitch, yaw, and roll.
Distance Measurement:
Estimates marker distance from the camera.

📽 Real-Time Visualization:

Join the Community!
Boost your computer vision projects with Aruco Pose Estimator.

Explore more on GitHub and don't forget to give us a star!

@MachineLearning_Programming