omyadav1983 Goto Github PK

awesome-5g

Awesome lists about 5G projects.

coursera-deep-learning-specialization

Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models

ddlo

Distributed Deep Learning-based Offloading for Mobile Edge Computing Networks

deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

edgecloudsim

EdgeCloudSim: An Environment for Performance Evaluation of Edge Computing Systems

facedetect

free5gc-stage-3

Open source 5G core network base on 3GPP R15

implementation_of_mec_papers

Implementation of submitted papers about Mobile Edge Computing (MEC).

mec_drl

Deep reinforcement learning for mobile edge computing

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

mobile-edge-computing

研究生论文

onos-form-cluster-docker

Docker container that can be used to form a cluster based on other docker instances of ONOS. Useful for docker-compose

pycoral

Python API for ML inferencing and transfer-learning on Coral devices

resources-allocation-in-the-edge-computing-environment-using-reinforcement-learning

Simulated the scenario between edge servers and users with a clear graphic interface. Also, implemented the continuous control with Deep Deterministic Policy Gradient (DDPG) to determine the resources allocation (offload targets, computational resources, migration bandwidth) in the edge servers

spring-social-samples

Samples of using Spring Social

tensorflow_edge

Tensorflow edge projects using Raspberry Pi 4 and Neural Compute Stick 2 and Coral.ai USB Accelerator

use-parallel-techniques-to-improve-performance-of-application-of-neural-network-on-edge-devices-

Introduction As researches on the topic of Deep Learning(DL) become mature, these neural networks are getting much heavier than past. That is to say, lots of computing power is required, including GPU and some parallel algorithm behind it, like distributing training. However, if we take power consumption or GPU utilization into consideration, in most case, many models waste a lot of resources. Thus, how to reach the maximum utilization of hardware accelerators while minimizing waste of energy becomes a vital issue. The central concept behind it is energy efficiency and hardware-aware deployment strategy. Based on these stuffs to extend, it is not only for training but also quite important for inference too. If the model is energy-efficient across platforms, then we could expect that it might have a great performance(latency) on the platforms which are power limited. Therefore, the objective we want to achieve is to use some parallel techniques to efficiently deploy models to a platform, which is not that powerful like server-class workstation, or be equipped with high performance accelerator like Titan, while still keeping its performance.

xxe-payloads

Security Testing for XXE attacks