Skip to main content

A tiny library for deep learning using numpy.

Project description

CraNet

CraNet is a python library for Deep Learning.

Installation

There are two ways to install CraNet

From pip

pip install cranet

From source

For now, This way is only available for linux.

Git clone repository

git clone https://github.com/shizuku/cranet.git

Build locally

cd cranet
./scripts/build_local_install.sh

Basic Information

Module Description
cranet.autograd tensor computation library based on numpy,集成了自动梯度的功能,支持张量的微分操作,所有需要微分的地方都用到了该库(包括梯度下降)
cranet.nn 基于tensor神经网络库,支持灵活地自定义神经网络结构(自定义层数,神经元个数,计算方式)
cranet.optim 优化器库,支持梯度下降神经网络参数
cranet.data 数据集库,以不同的方式处理各式各样的数据,以统一的方式将这些数据交接给神经网络,进行训练
cranet.utils 杂项,支持神经网络的储存与读入,辅助地显示一些计算过程

Release

Credits

License

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

cranet-0.2.0.tar.gz (32.5 kB view details)

Uploaded Source

Built Distribution

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

cranet-0.2.0-py3-none-any.whl (42.6 kB view details)

Uploaded Python 3

File details

Details for the file cranet-0.2.0.tar.gz.

File metadata

  • Download URL: cranet-0.2.0.tar.gz
  • Upload date:
  • Size: 32.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7

File hashes

Hashes for cranet-0.2.0.tar.gz
Algorithm Hash digest
SHA256 97958195e7ca917654374e8dafad14a21ee29e4c4cef5231c6e62626037fca08
MD5 7725b450ec48c594d1c9319a023d57b8
BLAKE2b-256 95eb3e55c93ba13cf3f5e7fa70338044ae37ef913fb98840680aec8fef7cfb86

See more details on using hashes here.

File details

Details for the file cranet-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: cranet-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 42.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7

File hashes

Hashes for cranet-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 46e7294c84af3d5aba9b3d39131ac20bf7553599ddcc9de569ff879bde52c9c0
MD5 4538177fbc29e3e9ee6a3705c56884ae
BLAKE2b-256 6b9300f83b2d642ecf7d094ad15473c68f5c5dcc8dbf963f7d14666a42635b94

See more details on using hashes here.

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