Skip to main content

Atiny is a gradient based PyTorch optimizer. Atiny uses half of Adam's memory to achieve results that are not inferior to Adam.

Project description

Atiny Optimizer

Atiny is a gradient based PyTorch optimizer. Atiny uses half of Adam's memory to achieve results that are not inferior to Adam.

image image

思路说明

不使用二阶动量,而是使用一阶动量与当前梯度计算每个参数的更新补偿. 内置了一个学习率衰减器,自动为每组参数个性化的学习率衰减.(需要参数:ldr) 使用ArcSinh函数影响向量模长实现权重衰减

Demo程序

demo程序在test.py文件中,直接运行即可得到此页面中Atiny与Adam的对比图.(依赖visdom) demo中构建了一个神经网络用简陋的方式对一个包含动态随机参数的公式生成的周期性曲线进行预测.

Install

pip install Atiny

Use

from Atiny import Atiny
...
optimizer=Atiny(moduel.parameters(),lr=lr,ldr=ldr,weight_decay=weight_decay)

HomePage

https://github.com/PsycheHalo/Atiny/

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

atiny-0.0.1.tar.gz (10.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

Atiny-0.0.1-py3-none-any.whl (10.5 kB view details)

Uploaded Python 3

File details

Details for the file atiny-0.0.1.tar.gz.

File metadata

  • Download URL: atiny-0.0.1.tar.gz
  • Upload date:
  • Size: 10.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for atiny-0.0.1.tar.gz
Algorithm Hash digest
SHA256 a47f8e0184c17f9a53a950f938967a1d5e8422e27dbc0fdab6633a899866b17f
MD5 b2ca6b8f37b0b64f290a19f486a80690
BLAKE2b-256 027bc415baa517d2017600b0a6ea7f55079bfc06e2ac0c7d0e241f555f17f08d

See more details on using hashes here.

Provenance

The following attestation bundles were made for atiny-0.0.1.tar.gz:

Publisher: python-publish.yml on PsycheHalo/Atiny

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file Atiny-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: Atiny-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 10.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for Atiny-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 8614cf6842cb1b5e7123c1ba0771c76472789597148ceddfbe97287c7f08eca0
MD5 fcc4c4b7237327250bb1989b2b393f8d
BLAKE2b-256 cade3b5f906b22dc1d39db349b1ea3363c6d0d2068c9714150c6df9cd9206985

See more details on using hashes here.

Provenance

The following attestation bundles were made for Atiny-0.0.1-py3-none-any.whl:

Publisher: python-publish.yml on PsycheHalo/Atiny

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page