PyTorch library for solving imaging inverse problems using deep learning

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

PRML algorithms implemented in Python

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

NYU Deep Learning Spring 2020

This repo contains a curative list of robot learning (mainly for manipulation) resources.

Learn how to design, develop, deploy and iterate on production-grade ML applications.

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …

A collection of academic papers / Git repos / conference talks / frameworks / tools related to cellular security and privacy.

2024.3.10 This project utilizes deep reinforcement learning methods for computation offloading and resource allocation in edge computing systems.

[TMI 2024] "High-Frequency Space Diffusion Model for Accelerated MRI"

Teaching material for wireless communications

18.06 course at MIT

Important concepts in numerical analysis and related areas

Teaching material for Digital Communications

Multi-agent Deep Reinforcement Learning for Efficient Computation Offloading in Mobile Edge Computing

Reinforcement learning resources curated

This advanced and complex project implements an AI-powered optimization system for 5G Open RAN networks. Using machine learning and deep learning, the system optimizes network performance by detect…

SwinIR: Image Restoration Using Swin Transformer (official repository)

Simple labs for software defined radios (SDRs).

Cloud Native MEC Platform (CNMP) represents a cloud native MEC environment based on free5gc, managed under 5GZORRO

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.