معرفی شرکت ها

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

توضیحات

Pytorch based deep learning library focussed on providing computationally efficient low resource methods and algorithms for NLP

ویژگی	مقدار
سیستم عامل	-
نام فایل	Fluence-0.1.7
نام	Fluence
نسخه کتابخانه	0.1.7
نگهدارنده	[]
ایمیل نگهدارنده	[]
نویسنده	Prajjwal Bhargava
ایمیل نویسنده	prajjwalin@pm.me
آدرس صفحه اصلی	https://github.com/prajjwal1/fluence
آدرس اینترنتی	https://pypi.org/project/Fluence/
مجوز	Apache

<p align="center"> <img src="https://raw.githubusercontent.com/prajjwal1/fluence/master/docs/logo.png" width="500"> <br /> <br /> <a href="https://github.com/prajjwal1/fluence/actions"><img alt="Build Status" src="https://github.com/prajjwal1/fluence/workflows/build/badge.svg" /></a> <a href="https://github.com/prajjwal1/fluence/releases"><img alt="Latest Release" src="https://img.shields.io/pypi/v/fluence"/></a> <a href="https://github.com/prajjwal1/fluence/blob/master/LICENSE"><img alt="Apache" src="https://img.shields.io/github/license/prajjwal1/fluence" /></a> <a href="https://codecov.io/gh/prajjwal1/fluence"><img src="https://codecov.io/gh/prajjwal1/fluence/branch/master/graph/badge.svg" /></a> ------------------------------------------------------------------------------- Fluence is a Pytorch based deep learning library focussed on providing computationally efficient, low resource methods and algorithms for NLP. Although the main focus is to provide support with transformers for NLP tasks, it can be extended with other domains and architectures as well. Currently in pre-alpha stage. <details> <summary>List of implemented papers</summary> #### Adaptive Methods - [Adaptive Attention Span in Transformers (ACL 2019)](https://arxiv.org/abs/1905.07799) - [Adaptively Sparse Transformers (EMNLP 2019)](https://arxiv.org/abs/1909.00015) - [Reducing Transformer Depth on Demand with Structured Dropout (ICLR 2020)](https://arxiv.org/abs/1909.11556) #### Meta Learning - [Model Agnostic Meta Learning (ICML 2017)](https://arxiv.org/abs/1703.03400) #### Debiasing - [Learning Robust Representations by Projecting Superficial Statistics Out (ICLR 2019)](https://openreview.net/pdf?id=rJEjjoR9K7) ------------------------------------------------------------------------------- </details> - [Installation](#installing) - [Overview](#overview) ## Why Fluence ? Fluence is targeted towards two main goals: 1. Low resource / computationally efficient algorithms 2. Algorithms that either enhance our understanding of current methods or show where SoTA methods fail. It is as straightforward to use as HF Transformers, and fully integrates with Pytorch. ## Installing For stable version: ```bash pip3 install --user fluence ``` For development version (recommended): ```bash git clone https://github.com/prajjwal1/fluence cd fluence python3 setup.py install --user ``` ## Overview The library contains implementation for the following approaches (many more to come): - [Adaptive Methods](https://github.com/prajjwal1/fluence/wiki/Importance-sampling) - [Meta Learning](https://github.com/prajjwal1/fluence/wiki/Meta-Learning) - [Optimizers](https://github.com/prajjwal1/fluence/wiki/Optimizers) - [Importance Sampling](https://github.com/prajjwal1/fluence/wiki/Importance-sampling) - [Siamese Methodology](https://github.com/prajjwal1/fluence/wiki/Siamese-Transformers) - [Debiasing](https://github.com/prajjwal1/fluence/wiki/Debiasing) ## Documentation Please head to this [link](https://github.com/prajjwal1/fluence/wiki) to learn how you can integrate fluence with your workflow. Since it's an early release, there might be bugs here and there. Please file an issue if you encounter one. ### Contribution You can contribute by either filing an issue or sending a Pull Request (if you encounter any bug or want some features to be added). Please checkout the [contributing guide](https://github.com/prajjwal1/fluence/blob/master/CONTRIBUTING.md) for more details. ### Tests Fluence comes with an [extensive test suite](https://github.com/prajjwal1/fluence/tree/master/tests). Each and every module has been tested before it comes into master branch. ``` pytest tests/ -v ``` Author: Prajjwal Bhargava ([@prajjwal_1](https://twitter.com/prajjwal_1))

نیازمندی

مقدار	نام
-	numpy
>=4.27	tqdm
-	transformers
-	higher
-	pandas
-	dataclasses

زبان مورد نیاز

مقدار	نام
>=3.6	Python

نحوه نصب

نصب پکیج whl Fluence-0.1.7:

pip install Fluence-0.1.7.whl

نصب پکیج tar.gz Fluence-0.1.7:

pip install Fluence-0.1.7.tar.gz