Models

Bonsai: Gradient Boosted Trees + Bayesian Optimization

Bonsai Bonsai is a wrapper for the XGBoost and Catboost model training pipelines that leverages Bayesian optimization for computationally efficient hyperparameter tuning. Despite being a very small package, it has access to nearly all of the configurable parameters in XGBoost and CatBoost as well as the BayesianOptimization package allowing users to specify unique objectives, metrics, parameter search ranges, and search policies. This is made possible thanks to the strong similarities between both libraries. $ pip install bonsai-tree References/Dependencies: Why use […]

Read more
Transformer

AST: Audio Spectrogram Transformer

AST This repository contains the official implementation (in PyTorch) of the Audio Spectrogram Transformer (AST) proposed in the Interspeech 2021 paper AST: Audio Spectrogram Transformer (Yuan Gong, Yu-An Chung, James Glass). AST is the first convolution-free, purely attention-based model for audio classification which supports variable length input and can be applied to various tasks. We evaluate AST on various audio classification benchmarks, where it achieves new state-of-the-art results of 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy […]

Read more
Security

Helps to quickly spot interesting security-related activity in Windows Event Viewer files

evtx-hunter evtx-hunter helps to quickly spot interesting security-related activity in Windows Event Viewer (EVTX) files. It can process a high number of events quickly, making it suitable for use during investigations and hunting activities across a high number of collected events. evtx-hunter is a Python tool that generates a web report of interesting activity observedin EVTX files. The tool comes with a few predefined rules to help you get going. This includesrules to spot for example: The first time a […]

Read more
Language Models

Pretrained model on Marathi language using a masked language modeling objective

RoBERTa base model for Marathi Language (मराठी भाषा) Pretrained model on Marathi language using a masked language modeling (MLM) objective. RoBERTa was introduced inthis paper and first released inthis repository. We trained RoBERTa model for Marathi Language during community week hosted by Huggingface 🤗 using JAX/Flax for NLP & CV jax. RoBERTa base model for Marathi language (मराठी भाषा) Model description Marathi RoBERTa is a transformers model pretrained on a large corpus of Marathi data in a self-supervised fashion. Intended […]

Read more
GUI

A hotkey manager that runs in the system tray

PySimpleHotkey A hotkey manager that runs in the system tray. Uses PySimpleGUI for the GUI and the system tray. This project uses these pip installable packages: PySimpleGUI psgtray keyboard This project is a mash-up of some PySimpleGUI demo programs and a program called pingmote. The pingmote project is the origin of the keyboard handler. A big thank you to @dchen327 for the code and inspiration. The system tray code is from the psgtray demo program. The 2 utilities that are […]

Read more
Tool

A tool to bypass negative HTTP status codes on the client side

4xxBypasser un outil pour bypasser les code d’états HTTP négatif coté client ( 4xx ) git clone https://github.com/RistBS/4xxBypasser cd 4xxBypasser && sudo pip3 install -r requirements.txt sudo python3 4xxbypasser.py Arguments/options disponibles : Proxy : mettez des proxies http ( peut éviter des refus de connexion ) Params : ajoutez des paramètres si jamais le code d’états l’indique ( 401 par ex ) Path : le chemin qui renvoie le code 4xx Format pour les args Proxy et Params : Params […]

Read more
Raspberrypi

A low power 1U Raspberry Pi cluster server for inexpensive colocation

Raspberry Pi 1U Server There are server colocation providers that allow hosting a 1U server for as low as $30/month, but there’s a catch: There are restrictions on power usage (1A @ 120v max, for example) because they’re expecting small and power-efficient network equipment like firewalls. This repo is about designing a server that fits within the 1U space and 1A @ 120v power constraint while maximizing computing power, storage, and value. GitHub https://github.com/pawl/raspberry-pi-1u-server    

Read more
Segmentation

Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery

FactSeg FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery (TGRS) by Ailong Ma, Junjue Wang*, Yanfei Zhong* and Zhuo Zheng This is an official implementation of FactSeg in our TGRS paper “FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery“ Citation If you use FactSeg in your research, please cite our coming TGRS paper. @ARTICLE{FactSeg, author={Ma Ailong, Wang Junjue, Zhong Yanfei and Zheng Zhuo}, journal={IEEE Transactions on Geoscience and Remote Sensing}, […]

Read more
Scripts

Python script designed to search and fetch direct download links from nxbrew.com

SwitchGamesDownloader nxbrew.com is a website, accessible only using a proxy, where the majority of games for the Nintendo Switch are stored, this script will ask you for the game to be searched in the aformentioned website then tunnel your request through hide.me providing you with the final download link skipping all those filthy scam pages and pop-up tabs. PRE-REQUISITES You need to have Python3 installed in PATH You need to have Chrome installed You will need to download Chromedriver.exe and […]

Read more
Machine Learning

Clockwork Variational Autoencoders using JAX and Flax

Clockwork VAEs in JAX/Flax Implementation of experiments in the paper Clockwork Variational Autoencoders (project website) using JAX and Flax, ported from the official TensorFlow implementation. Running on a single TPU v3, training is 10x faster than reported in the paper (60h -> 6h on minerl). Method Clockwork VAEs are deep generative model that learn long-term dependencies in video by leveraging hierarchies of representations that progress at different clock speeds. In contrast to prior video prediction methods that typically focus on […]

Read more
1 … 561 562 563 564 565 … 935