Deep Learning Basics (lecture notes)

Romain Tavenard
Jul 20, 2023
@machine_learning_and_DL

Machine Learning (lecture notes)

Winter 2024

@machine_learning_and_DL

Statistical Learning Theory(Winter 2016)

Percy Liang
@machine_learning_and_DL

SOTA🚀 YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

☄️ Github
☄️ Paper

ورژن ۹ مدل YOLO در چهار سایز ۷/۲ میلیون، ۲۰/۱ میلیون و ۲۵/۵ میلیون و ۵۸/۱ میلیون پارامتر منتشر شد!!!

مقاله:
https://arxiv.org/abs/2402.13616

کد:
https://github.com/WongKinYiu/yolov9

🩻 Pose via Ray Diffusion 🩻

👉Novel distributed representation of camera pose that treats a camera as a bundle of rays. Naturally suited for set-level transformers, it's the new SOTA on camera pose estimation. Source code released 💙

👉Review https://t.ly/qBsFK
👉Paper arxiv.org/pdf/2402.14817.pdf
👉Project jasonyzhang.com/RayDiffusion
👉Code github.com/jasonyzhang/RayDiffusion

#هوش_مصنوعی #مقاله #سورس_کد
💎 مدل YOLOv9 منتشر شد.
- سریعتر، دقیقتر و بهینه‌تر از مدل‌های مشابه
📎 دانلود مقاله (pdf)
💻 دانلود سورس کد (Github)
YOLOv9 is out 🔥
📄 We combined the proposed PGI and GELAN, then designed a new generation of YOLO object detection system, which we call YOLOv9.
🔻share with your friends🔻
🔹@OpenCV_olc🔹

ابزارهای لازم برای یادگیری ماشین
@DocPython

کتابخانه لاکپشت در پایتون

برگه تقلب یادگیری عمیق

مدل YOLOv9 هم اومد. الان میتونید به صورت لوکال توی browser به صورت تقریبا real time اشیا را تشخیص بدید. نیازی هم به سرور ندارید


🔗 Demo: https://hf.co/spaces/Xenova/yolov9-web

https://blog.roboflow.com/train-yolov9-model/

https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov9-object-detection-on-custom-dataset.ipynb

https://github.com/WongKinYiu/yolov9

https://github.com/roboflow/notebooks

🆔 @Ai_Tv

CyberDemo

Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation

We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates across various tasks and exhibits generalizability with previously unseen objects. For example, it can rotate novel tetra-valve and penta-valve, despite human demonstrations only involving tri-valves. Our research demonstrates the significant potential of simulated human demonstrations for real-world dexterous manipulation tasks.

paper page: https://huggingface.co/papers/2402.14795


🆔

⭐ MATH-Vision Dataset 🕹

😏 MATH-V is a curated dataset of 3,040 HQ mat problems with visual contexts sourced from real math competitions. Dataset released 📱

😏 Review: https://t.ly/gmIAu

🤨 Paper: arxiv.org/pdf/2402.14804.pdf

🥺 Project: mathvision-cuhk.github.io/

👉 Code: github.com/mathvision-cuhk/MathVision

Deep Learning with torch:: CHEAT SHEET

یادگیری با نظارت؛ بدون نظارت و یادگیری تقویتی
@Docpython

Mathematical Foundations of Machine

Learning Lectures on YouTube

Seongjai Kim
Department of Mathematics and Statistics
Mississippi State University

Updated: February 14, 2024

@machine_learning_and_DL

مدل بنیادین گوگل برای درک ویدئو منتشر شد!!!

مدل VideoPrism یک ViFM یا مدل بنیادین ویدئو‌ست که برخلاف مدل‌های قبلی مثل VideoCLIP برای دامنه‌ی وسیعی از تسک‌ها از جمله classification و localization و retrieval و captioning و question answering قابل استفاده‌ست.

https://blog.research.google/2024/02/videoprism-foundational-visual-encoder.html

🌟 Discover 6DRepNet: The Ultimate Head Pose Estimation Model!

Features:
* State-of-the-art accuracy
* Comprehensive tools for training, testing, and inference
* Easy setup with conda
* Supports multiple datasets

Watch the performance showcase on GitHub for future advancements.

[Source Code] [Paper]

کتابخانه لاکپشت در پایتون