Skip to main content

RU Proverbs generator

Project description

RU Proverbs AI module

PyPI version

This module provides API that allows to generate Russian Proverbs with the power of AI.

Requirements

For Windows builds:

In the current version we use Python 3.7.6, Tensorflow 2.3.1 and CUDA 10.1.

  1. Python 3.7.x. x64 (tested with Python 3.7.6x64).

  2. Properly installed Tensorflow inside the virtual env:

    2.1 Install virtual env: python -m venv .venv.

    2.2 Upgrade pip: python -m pip install --upgrade pip.

    2.3 Upgrade setuptools: pip install --upgrade setuptools.

    2.3 Install Tensorflow: pip install --upgrade tensorflow

    2.4 Optionally install and configure CUDA support.

  3. Install other requirements: pip install --upgrade -r requirements.txt

Configure CUDA

  1. Download CUDA Toolkit and unpack into e.g. D:\DevTools\cuda\v10.1.

  2. Download matching cuDNN version (e.g. v7.6.5 for CUDA 10.1) and unpack under the versioned CUDA folder, e.g. D:\DevTools\cuda\v10.1\cudnn.

  3. Add CUDA paths to environment variables and PATH:

    Create CUDA_HOME and CUDA_PATHS env variables with the following values:

    SET CUDA_HOME=D:\DevTools\cuda\v10.1
    SET CUDA_PATHS=%CUDA_HOME%\bin;%CUDA_HOME%\include;%CUDA_HOME%\extras;%CUDA_HOME%\libnvvp;%CUDA_HOME%\cudnn\bin;
    

    Add CUDA_PATHS to PATH: SET PATH=%CUDA_PATHS%;%PATH%.

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

ru_proverbs-1.1.0.tar.gz (2.9 kB view hashes)

Uploaded source

Built Distribution

ru_proverbs-1.1.0-py3-none-any.whl (1.7 MB view hashes)

Uploaded py3

Supported by

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