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.
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
1 maintainer
Metadata
1 maintainer
Release files for Atiny 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| atiny-0.0.4.tar.gz | 10.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| atiny-0.0.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 21.2 kB
Release files / atiny-0.0.4.tar.gz
| Download URL | atiny-0.0.4.tar.gz |
|---|---|
| Size | 10.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
226058e46303e54b0c31dd48537e8f55d29e84966ad6cc8fe5eb87fed24533de
|
|
BLAKE2b-256 checksum How to use checksums |
0c5a510b6647be8ccc0b0df690e26e6997d3a27ae726324bae0e413343305df0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 3, 2025.
Transparency logRelease files / atiny-0.0.4-py3-none-any.whl
| Download URL | atiny-0.0.4-py3-none-any.whl |
|---|---|
| Size | 10.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5016313984544b6b69ebf63d0b2a006130e3ef2ad57206d622e85f9709b4bb0a
|
|
BLAKE2b-256 checksum How to use checksums |
aa0008fdbeb6e177381df890a6882686c25cf54a5ee5b035fdd932a3b6b16d45
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 3, 2025.
Transparency log
