Language Models

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

This is the official implementation for “Frustratingly Simple Pretraining Alternatives to Masked Language Modeling” (EMNLP 2021). Requirements torch transformers datasets scikit-learn tensorflow spacy How to pre-train 1. Clone this repository git clone https://github.com/gucci-j/light-transformer-emnlp2021.git 2. Install required packages cd ./light-transformer-emnlp2021 pip install -r requirements.txt requirements.txt is located just under light-transformer-emnlp2021. We also need spaCy’s en_core_web_sm for preprocessing. If you have not installed this model, please run python -m spacy download en_core_web_sm. 3. Preprocess datasets cd ./src/utils python preprocess_roberta.py –path=/path/to/save/data/ You need […]

Read more
Asyncio

Fully asynchronous trace.moe API wrapper

Fully asynchronous trace.moe API wrapper Installation You can install the stable version from PyPI: $ pip install aiomoe Or get it from github: $ pip install https://github.com/FeeeeK/aiomoe/archive/refs/heads/master.zip Usage Get info about your account import asyncio from aiomoe import AioMoe tm = AioMoe() # or AioMoe(token=”xxxxxxxx”) async def main(): me = await tm.me() print(me) print(f”Used quota: {me.quota_used}/{me.quota}”) asyncio.run(main()) The output will be like this: User(error=None, id=’your ip’, priority=0, concurrency=1, quota=1000, quota_used=0) Used quota: 0/1000 Search anime import asyncio from aiomoe import […]

Read more
AUTONOMOUS DRIVING

This solves the autonomous driving issue which is supported by deep learning technology

This solves the autonomous driving issue which is supported by deep learning technology. Given a video, it splits into images and predicts the angle of turning for each frame. An autonomous car (also known as a driverless car, self-driving car, and robotic car) is a vehicle that is capable of sensing its environment and navigating without human input. Autonomous cars combine a variety of techniques to perceive their surroundings, including radar, laser light, GPS, odometry, and computer vision. Advanced control […]

Read more
Security

GitLab CI security tools runner

Описание проекта: Данный проект является вариантом реализации DevSecOps практик, на базе: Используйте данный репозиторий чтобы построить безопасность в цикле CI/CD. Quick Start Склонировать к себе Common Security Pipeline Исправить все места где встречается комментарий CHECK IT или FIX IT Изменить в ./pipeline/security_tools.yml путь до контейнеров с Security Tools Поднять у себя DefectDojo Прописать у себя в GitLab необходимые переменные: API-ключ Путь до DefectDojo для доступа к вашему DefectDojo в файле ./dd_prepare/dd_prepare.py. Если у вас используется Vault или аналогичное решение, то […]

Read more
Deep Learning

TFLearn: Deep learning library featuring a higher-level API for TensorFlow

TFlearn is a modular and transparent deep learning library built on top of Tensorflow. It was designed to provide a higher-level API to TensorFlow in order to facilitate and speed-up experimentations, while remaining fully transparent and compatible with it. TFLearn features include: Easy-to-use and understand high-level API for implementing deep neural networks, with tutorial and examples. Fast prototyping through highly modular built-in neural network layers, regularizers, optimizers, metrics… Full transparency over Tensorflow. All functions are built over tensors and can […]

Read more
Research

ipython-based environment for conducting data-driven research in a consistent and reproducible way

REP is ipython-based environment for conducting data-driven research in a consistent and reproducible way. Main features: unified python wrapper for different ML libraries (wrappers follow extended scikit-learn interface) Sklearn TMVA XGBoost uBoost Theanets Pybrain Neurolab MatrixNet service(available to CERN) parallel training of classifiers on cluster classification/regression reports with plots interactive plots supported smart grid-search algorithms with parallel execution research versioning using git pluggable quality metrics for classification meta-algorithm design (aka ‘rep-lego’) REP is not trying to substitute scikit-learn, but extends […]

Read more
Machine Learning

Regularized Greedy Forest: A tree ensemble machine learning method described

Regularized Greedy Forest Regularized Greedy Forest (RGF) is a tree ensemble machine learning method described in this paper. RGF can deliver better results than gradient boosted decision trees (GBDT) on a number of datasets and it has been used to win a few Kaggle competitions. Unlike the traditional boosted decision tree approach, RGF works directly with the underlying forest structure. RGF integrates two ideas: one is to include tree-structured regularization into the learning formulation; and the other is to employ […]

Read more
1 … 500 501 502 503 504 … 946