June 25, 2021 Optimization

How Do Adam and Training Strategies Help BNNs Optimization?

AdamBNN This is the pytorch implementation of our paper “How Do Adam and Training Strategies Help BNNs Optimization?”, published in ICML 2021. ![](https://github.com/liuzechun0216/images/raw/master/AdamBNN_github.jpg =60%x) In this work, we explore the intrisic reasons why Adam is superior to other optimizers like SGD for BNN optimization and provide analytical explanations that support specific training strategies. By visualizing the optimization trajectory, we show that the optimization lies in extremely rugged loss landscape and the second-order momentum in Adam is crucial to revitalize the […]

June 25, 2021 Tool

A python tool developed to bruteforce Apache Tomcat manager username and password

Tomcter Python Tomcat Login Bruteforce ⚡ Installing / Getting started A quick guide of how to install and use Tomcter. 1. Clone the repository with git clone https://github.com/oppsec/tomcter.git 2. Install the libraries with pip3 install -r requirements.txt 3. Insert the targets URL on src/core/data/urls.txt file (ex: https://www.google.com) 4. Run Tomcter with python3 main.py 🐳 Docker If you want to use Tomcter in a Docker container, follow this commands: 1. Clone the repository – git clone https://github.com/oppsec/tomcter.git 2. Build the image […]

June 25, 2021 AWS

Create a Neo4J graph of users and roles trust policies within an AWS Organization

AWS_ORG_MAPPER This tool uses sso-oidc to authenticate to the AWS organization. Once authenticated the tool will attempt to enumerate all users and roles in the organization and map their trust relations. The graph can be explored using Neo4j desktop or web client. Below you can find some sample queries that can help extract useful information from the graph. Using this tool users can discover how role trusts are delegated in the organization and can help identify improve account isolation within […]

June 25, 2021 Natural Language Processing

A method to pre-train general purpose natural language models

TunBERT People in Tunisia use the Tunisian dialect in their daily communications, in most of their media (TV, radio, songs, etc), and on the internet (social media, forums). Yet, this dialect is not standardized which means there is no unique way for writing and speaking it. Added to that, it has its proper lexicon, phonetics, and morphological structures. The need for a robust language model for the Tunisian dialect has become crucial in order to develop NLP-based applications (translation, information […]

June 25, 2021 Network

Group Fisher Pruning for Practical Network Compression

FisherPruning Group Fisher Pruning for Practical Network Compression(ICML2021) NOTES All models about detection has been released. The classification models will be released later, because we want to refactor all our code into a Hook , so that it can become a more general tool for all tasks in OpenMMLab. We will continue to improve this method and apply it to more other tasks, such as segmentation and pose. The layer grouping algorithm is implemtated based on the AutoGrad of Pytorch, […]

June 25, 2021 Neural Network

Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

ContextNet ContextNet has CNN-RNN-transducer architecture and features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules.Also, ContextNet supports three size models: small, medium, and large. ContextNet uses the global parameter alpha to control the scaling of the model by changing the number of channels in the convolution filter. This repository contains only model code, but you can train with ContextNet at openspeech. Model Architecuture Configuration of the ContextNet encoder If you choose the […]

June 25, 2021 Raspberrypi

Monorepo for my Raspberry Pi dashboard and GPS satellite listener

pi dashboard Monorepo for my Raspberry Pi dashboard and GPS satellite listener. It includes: a module system allows different features to be toggled on and off so you don’t need my exact hardware setup. It also allows multiple Pis to use the same server. :house: a Windows 98 themed dashboard. :satellite: view the list of visible GPS satellites from a GPS hardware device. :printer: receive printer messages to a POS58 compatible printer. :thermometer: live temperature/humidity collected from an AMxx compatible […]

June 25, 2021 Machine Learning

A python library that lets you customize automated machine learning

nylon An intelligent, flexible grammar of machine learning. Nylon is a python library that lets you customize automated machine learning workflows through a concise, JSON syntax. It provides a built in grammar, in which you can access different operations in ML with the english language. Installation Install latest release version: pip install -U nylon-ai Install directory from github: git clone https://github.com/Palashio/nylon.git cd nylon-ai pip install . Usage: the basics A new Polymer object should be created everytime you’re working with […]

June 25, 2021 PyTorch

A variety of sequence model architectures from scratch in PyTorch

Sequence Models This repository implements a variety of sequence model architectures from scratch in PyTorch. Effort has been put to make the code well structured so that it can serve as learning material. The training loop implements the learner design pattern from fast.ai in pure PyTorch, with access to the loop provided through callbacks. Detailed logging and graphs are also provided with python logging and wandb. Additional implementations will be added. Setup Using Miniconda/Anaconda: cd path_to_repo conda create –name –file […]

June 25, 2021 Machine Learning

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

implicit_depth This repository maintains the official implementation of our CVPR 2021 paper: RGB-D Local Implicit Function for Depth Completion of Transparent Objects By Luyang Zhu, Arsalan Mousavian, Yu Xiang, Hammad Mazhar, Jozef van Eenbergen, Shoubhik Debnath, Dieter Fox Requirements The code has been tested on the following system: Ubuntu 18.04 Nvidia GPU (4 Tesla V100 32GB GPUs) and CUDA 10.2 python 3.7 pytorch 1.6.0 Installation Docker (Recommended) We provide a Dockerfile for building a container to run our code. More […]

« 1 … 634 635 636 637 638 … 973 »