Skip to main content

This library is an my improved version of "Deep Learning from Basic 3".

Project description

K_DeZero

Overview

This library is an my improved version of "Deep Learning from Basic 3". (In production)

Requirement

  • Python3.8
  • If you use gpu, cupy
  • If you want to visualize the model, install graphviz
  • For details, see requirements.txt

Usage

Method1:

pip install kdezero

Method2:

git clone https://github.com/kotabrog/K_DeZero.git
cd kdezero
python setup.py sdist
pip install dist\kdezero-2.1.tar.gz

Then you will be able to use "kdezero".

sample

Look at samples.

Features

This library can:

  • Backpropagation-enabled variables can be used like numpy
  • Contains basic machine learning parts
  • Some support gpu
  • Visualize model configuration using graphviz

Author

twitter

Licence

MIT

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

kdezero-2.1.tar.gz (23.4 kB view details)

Uploaded Source

File details

Details for the file kdezero-2.1.tar.gz.

File metadata

  • Download URL: kdezero-2.1.tar.gz
  • Upload date:
  • Size: 23.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.8

File hashes

Hashes for kdezero-2.1.tar.gz
Algorithm Hash digest
SHA256 5e6cc0e7952b67bc5f1cf7e16d579950df0cffa33fb1f894527e3245df342ff3
MD5 c83a47c6d72b587ebc806aa27a45490c
BLAKE2b-256 af7f873bff9d9f2528f73831e96a8121bebab611638198cc710b169b2ac1ef61

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